© 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. 35157
    Prev
    Next
    INDEX
    Explanations

    cases, sins, Table, Year, Castle

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

    hierarchies, values, comics, aircraft

    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
    农
    0.44
    师
    0.43
     uppermost
    0.43
    湖
    0.43
    łą
    0.42
    گرد
    0.42
     unsupported
    0.42
    连
    0.42
    امین
    0.41
    й
    0.41
    POSITIVE LOGITS
     វា
    0.53
     букмекер
    0.52
     önemlidir
    0.51
     遅く
    0.50
     Chirurgien
    0.47
     निर्यात
    0.47
    ík
    0.46
     tanıml
    0.46
     Flüss
    0.46
     Überblick
    0.45
    Activations Density 0.000%

    No Known Activations