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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99148
    Prev
    Next
    INDEX
    Explanations

    critical residues and positions

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

    references to amino acid residues in scientific literature about proteins and molecular biology.

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

    The neuron strongly activates on numeric values in scientific contexts (e.g. residue numbers, percentages, position indices).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    f
    -1.78
     cœurs
    -1.73
     ruines
    -1.64
    und
    -1.62
     estante
    -1.55
    </h4>
    -1.54
     desenli
    -1.52
    并不
    -1.49
     graden
    -1.46
    u
    -1.46
    POSITIVE LOGITS
    翆
    1.83
     kemudian
    1.68
     niezbęd
    1.61
     Aseg
    1.53
     this
    1.52
     различни
    1.52
    щают
    1.49
     Relacion
    1.46
    Nella
    1.45
    有不少
    1.44
    Activations Density 0.039%

    No Known Activations