© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3258
    Prev
    Next
    INDEX
    Explanations

    options lists, questions

    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_7_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
     एजुकेशन
    2.28
     menyampaikan
    2.25
     एजु
    2.17
     Segurança
    2.16
     setSnackbar
    2.15
     Lobkovic
    2.13
     Ztg
    2.11
    <unused1493>
    2.10
     mengadakan
    2.10
    yyati
    2.09
    POSITIVE LOGITS
    »
    1.65
    «
    1.29
    county
    1.23
    xref
    1.21
    heritage
    1.20
    almost
    1.18
     once
    1.17
    rolled
    1.17
    œ
    1.16
    once
    1.14
    Activations Density 0.004%

    No Known Activations