© 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. 28745
    Prev
    Next
    INDEX
    Explanations

    balance is due

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

    trends and urges

    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
    和服务
    0.44
     منزل
    0.42
    ?—
    0.40
     vivienda
    0.40
    தா
    0.39
    了
    0.39
    ంటే
    0.38
     সিস্টেম
    0.38
    锲
    0.37
    上了
    0.37
    POSITIVE LOGITS
    অগ্র
    0.53
    ahiran
    0.52
     レ
    0.51
     selectivity
    0.51
     querying
    0.49
     چال
    0.49
    commodity
    0.48
     ryzy
    0.46
    सामान्यीकृत
    0.46
    oL
    0.46
    Activations Density 0.000%

    No Known Activations