© 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. 59709
    Prev
    Next
    INDEX
    Explanations

    academic and financial contexts

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

    Stimulation fan Commons Corrosion Renewal Rhetorical Potential

    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
    $，
    0.50
     combinación
    0.45
     consentimiento
    0.45
     persönlichen
    0.45
     combinatie
    0.44
    sequently
    0.44
     volledig
    0.43
    ië
    0.43
    意志
    0.43
     牛
    0.43
    POSITIVE LOGITS
    וס
    0.55
     Announces
    0.44
     adjacent
    0.44
     cms
    0.44
    ιος
    0.43
    +",
    0.43
    তো
    0.43
    쿱
    0.43
    Future
    0.42
    NT
    0.42
    Activations Density 0.000%

    No Known Activations