© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147047
    Prev
    Next
    INDEX
    Explanations

    program files paths

    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
    ftÂ
    0.71
    ភាគ
    0.66
     নিত্য
    0.66
    责任
    0.66
     hundreds
    0.64
    醅
    0.64
     connaissances
    0.63
    <unused1107>
    0.63
    ဟု
    0.62
    뤄
    0.62
    POSITIVE LOGITS
    ünüz
    0.77
    atora
    0.76
     Dale
    0.76
     sliding
    0.75
    ales
    0.75
    oking
    0.75
    Da
    0.72
    మే
    0.70
    wych
    0.70
    ALLE
    0.69
    Activations Density 0.000%

    No Known Activations