© 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. 29312
    Prev
    Next
    INDEX
    Explanations

    card and responsibility

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

    submission

    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
    0.49
     enunci
    0.49
     padre
    0.46
     paragra
    0.44
    厝
    0.44
     Handbook
    0.42
     passaggio
    0.42
     ທ
    0.42
     considér
    0.40
    FileInputExcel
    0.40
    POSITIVE LOGITS
    subarray
    0.51
    nullable
    0.48
    Bộ
    0.48
    helium
    0.47
    новить
    0.46
    твер
    0.44
    manufact
    0.44
    일본
    0.44
    itionen
    0.44
    })"
    0.44
    Activations Density 0.000%

    No Known Activations