© 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. 7609
    Prev
    Next
    INDEX
    Explanations

    other recommendations or related links

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

    relationship, connections, links

    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
    萫
    0.45
    菽
    0.44
     bertujuan
    0.43
     раствора
    0.43
    нтэр
    0.42
    <unused1112>
    0.42
     声
    0.42
    羮
    0.42
    劳动
    0.40
    环保
    0.40
    POSITIVE LOGITS
     other
    0.54
     previous
    0.52
     afflict
    0.48
     connect
    0.47
     linkage
    0.47
     kindred
    0.46
     connections
    0.46
     nearby
    0.46
     links
    0.46
    {"
    0.45
    Activations Density 0.000%

    No Known Activations