© 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. 90156
    Prev
    Next
    INDEX
    Explanations

    instructions and statements

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

    combination of basketball

    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
    现在的
    0.50
    ́ch
    0.50
    风险
    0.49
    Parrocchia
    0.49
    扃
    0.48
    佽
    0.47
    Jetzt
    0.47
    Vous
    0.47
    風險
    0.47
    谲
    0.47
    POSITIVE LOGITS
    ice
    0.49
    mata
    0.49
    ya
    0.48
     contoh
    0.48
     clima
    0.47
    equivariant
    0.47
    conto
    0.47
    monday
    0.47
    re
    0.46
     نوٹ
    0.46
    Activations Density 0.003%

    No Known Activations