© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115471
    Prev
    Next
    INDEX
    Explanations

    mutants, variants, analogs, and fragments

    np_acts-logits-general · gemini-2.5-flash-lite

    protein and genetic mutation nomenclature, especially amino acid sequences and protein variants.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on notation of specific amino‐acid substitutions (e.g. “G24S,” “D38N”) describing point mutations in proteins.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NGS
    -0.76
     бюдже
    -0.75
     Assignment
    -0.73
     inconsistency
    -0.70
    indications
    -0.70
    determination
    -0.69
    бия
    -0.69
    Usos
    -0.69
    champions
    -0.68
    Flashcards
    -0.66
    POSITIVE LOGITS
     mutant
    2.06
     mutants
    2.03
     variants
    1.87
     variant
    1.77
     derivatives
    1.54
     derivative
    1.53
     constructs
    1.38
     construct
    1.38
     versions
    1.29
     Mutant
    1.28
    Activations Density 0.329%

    No Known Activations