© 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. 163351
    Prev
    Next
    INDEX
    Explanations

    for destinations or purposes

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

    describing relationships or states

    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
     опор
    0.54
     甘
    0.53
     tit
    0.49
     দুদ
    0.49
     吃
    0.49
     Shet
    0.48
     titul
    0.47
     科
    0.47
    听
    0.47
    履
    0.47
    POSITIVE LOGITS
    utada
    0.49
    raj
    0.46
    isins
    0.46
     રાહ
    0.45
    étant
    0.43
    iral
    0.42
    SEARCH
    0.42
    ira
    0.42
    ô
    0.41
    estic
    0.41
    Activations Density 0.001%

    No Known Activations