© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116580
    Prev
    Next
    INDEX
    Explanations

    caravan heads

    np_acts-logits-general · gemini-2.5-flash-lite

    comprehensive resume descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     <%
    0.45
    arian
    0.42
     Gait
    0.42
     నగ
    0.41
     Automatic
    0.40
    这份
    0.40
    ފައި
    0.40
     facture
    0.40
     Meghna
    0.40
    这篇文章
    0.40
    POSITIVE LOGITS
    VENTORY
    0.49
    поль
    0.47
    থেষ্ট
    0.47
    વણી
    0.46
    passt
    0.46
    )+
    0.44
    কে
    0.44
     bidders
    0.44
    geti
    0.44
    )=\
    0.44
    Activations Density 0.000%

    No Known Activations