© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 150158
    Prev
    Next
    INDEX
    Explanations

    criminal proceedings, performance, oxygen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_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
    বৃত্তি
    0.76
    ამო
    0.71
    {
    0.69
    대는
    0.68
    대
    0.67
     நிறுத்த
    0.67
    indle
    0.66
    ft
    0.66
    adora
    0.64
     desist
    0.64
    POSITIVE LOGITS
     Pentecost
    0.89
     porous
    0.86
     Oxygen
    0.86
     oxygen
    0.84
     polygonal
    0.82
     Hered
    0.81
     ઓછા
    0.80
    <unused2042>
    0.80
     гуляць
    0.79
     spol
    0.79
    Activations Density 0.000%

    No Known Activations