© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 63
    Prev
    Next
    INDEX
    Explanations

    finger-related compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cparam
    1.63
    <unused298>
    1.61
    notlocked
    1.60
    coeffs
    1.55
    countery
    1.51
    <unused1821>
    1.50
    aadhar
    1.50
    getAvg
    1.46
    <unused2118>
    1.45
    <unused920>
    1.45
    POSITIVE LOGITS
     S
    1.67
     Sir
    1.60
     N
    1.53
     T
    1.52
     D
    1.52
     Gar
    1.50
     M
    1.49
     F
    1.47
     Man
    1.47
     L
    1.44
    Activations Density 2.494%

    No Known Activations