© 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. 172568
    Prev
    Next
    INDEX
    Explanations

    reporting factual statements

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

    positive outcomes and definitions

    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
     petitioned
    0.51
    claimed
    0.45
    }'
    0.45
     in
    0.45
     enforceable
    0.44
     monotonic
    0.44
     ＊
    0.44
     obsolete
    0.44
    イト
    0.44
     required
    0.43
    POSITIVE LOGITS
    쌌
    0.51
     pantalla
    0.50
     Servicios
    0.49
    탰
    0.49
     embarazo
    0.49
    ехал
    0.49
     Spain
    0.48
    岡田
    0.48
     confianza
    0.47
    ديث
    0.46
    Activations Density 0.001%

    No Known Activations