© 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. 251059
    Prev
    Next
    INDEX
    Explanations

    BOTTOM LINE

    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
     Mạnh
    0.48
     Centre
    0.47
     verhindert
    0.46
     Gue
    0.46
     Andorra
    0.44
     `=
    0.43
     Australia
    0.43
     বিশ্র
    0.43
     Sand
    0.43
     Perp
    0.43
    POSITIVE LOGITS
     speculators
    0.55
    होम
    0.50
    ਰੀ
    0.48
    ブレ
    0.48
    賺
    0.48
    ಕ್ಷ
    0.48
    לו
    0.48
     repurchase
    0.47
     cures
    0.47
    ミックス
    0.46
    Activations Density 0.001%

    No Known Activations