© 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. 245009
    Prev
    Next
    INDEX
    Explanations

    scripting elements

    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
    ación
    0.78
    '
    0.74
    are
    0.73
    ate
    0.70
    etes
    0.70
    uing
    0.68
    าว
    0.66
    was
    0.65
    0.65
    ning
    0.64
    POSITIVE LOGITS
    B
    0.78
    C
    0.70
    D
    0.70
    )。
    0.65
     dizer
    0.63
    លោក
    0.63
    》。
    0.62
     wohl
    0.61
    >(
    0.61
     可能
    0.61
    Activations Density 0.006%

    No Known Activations