© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3770
    Prev
    Next
    INDEX
    Explanations

    depends on circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    il
    0.89
    remainder
    0.86
    пу
    0.86
    тельство
    0.86
    only
    0.86
    質
    0.85
    U
    0.85
     uncertainty
    0.84
     Rest
    0.83
     Sp
    0.82
    POSITIVE LOGITS
     hyvin
    0.93
    ucional
    0.92
    <unused2142>
    0.92
    <unused1751>
    0.92
     çöze
    0.91
    GEBURTSORT
    0.90
    <unused2164>
    0.89
     ähm
    0.86
    uxi
    0.86
    劊
    0.85
    Activations Density 0.105%

    No Known Activations