© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84241
    Prev
    Next
    INDEX
    Explanations

    DNA insertion and deletion

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

    genetic mutations and DNA sequence variations in scientific text.

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

    This neuron primarily fires on numeric tokens and quantitative expressions (e.g. numbers, counts, measurements).

    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
     impart
    -0.84
    缀
    -0.75
     cầm
    -0.71
    istique
    -0.68
    нг
    -0.67
    áneamente
    -0.66
    ResId
    -0.66
     diaries
    -0.65
    CCL
    -0.65
     electrónico
    -0.65
    POSITIVE LOGITS
     insertions
    2.72
     insertion
    2.69
     deletion
    2.44
    insertion
    2.25
     insert
    2.23
     deletions
    2.20
     Insertion
    2.19
    Insertion
    2.06
    insert
    2.05
     Insert
    2.05
    Activations Density 0.105%

    No Known Activations