© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5122
    Prev
    Next
    INDEX
    Explanations

    "I" or punctuation

    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
     bustling
    1.16
     Schwann
    1.14
     toot
    1.13
     COMPLEXES
    1.13
    lsulfanyl
    1.12
    휠
    1.11
     quia
    1.11
     artisti
    1.09
     fungi
    1.08
     semplic
    1.06
    POSITIVE LOGITS
    可行
    1.02
    elines
    0.93
    >?,
    0.92
    budget
    0.91
     घ्या
    0.91
    его
    0.91
     budgets
    0.90
    يرو
    0.90
    ئے
    0.89
    annel
    0.88
    Activations Density 0.306%

    No Known Activations