© 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. 243998
    Prev
    Next
    INDEX
    Explanations

    accounts, switches, injected, più belle, evergreen content, child pages

    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
    Transformation
    0.45
     modalCard
    0.43
     평가
    0.43
    Savings
    0.43
     Savings
    0.43
     transition
    0.42
    의
    0.42
     comply
    0.42
     退
    0.41
    を得
    0.41
    POSITIVE LOGITS
    füh
    0.50
     Zap
    0.48
    Zap
    0.46
    وازي
    0.46
    ["
    0.45
    ahooks
    0.45
    டப்பட்டது
    0.45
     ors
    0.44
     jel
    0.44
    रासत
    0.44
    Activations Density 0.000%

    No Known Activations