© 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. 4490
    Prev
    Next
    INDEX
    Explanations

    discussing actions and focus

    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
    一
    0.65
    나
    0.58
     problema
    0.56
    pu
    0.55
     a
    0.54
    q
    0.52
    po
    0.52
    posto
    0.52
    t
    0.52
    ૧
    0.52
    POSITIVE LOGITS
     precincts
    0.54
    MathMarks
    0.54
    ረጃ
    0.50
     jurisdictions
    0.50
     edific
    0.49
     holdings
    0.48
    '}}>
    0.47
     forbids
    0.47
     outfits
    0.47
     ateliers
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.