© 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. 235069
    Prev
    Next
    INDEX
    Explanations

    annual report, sustained business, implied warranties

    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
     Muslim
    0.50
     counsell
    0.50
     ३
    0.49
     bloquear
    0.49
     মুহাম্মদ
    0.49
     Вулкан
    0.49
    ர
    0.47
    陝
    0.47
     Phật
    0.47
     ၁
    0.47
    POSITIVE LOGITS
    Mark
    0.50
    _
    0.49
    gång
    0.47
    EL
    0.46
    ACK
    0.46
    end
    0.46
    ING
    0.46
    ELS
    0.46
    offset
    0.46
    SEL
    0.46
    Activations Density 0.000%

    No Known Activations