© 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. 239181
    Prev
    Next
    INDEX
    Explanations

    party responsible

    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
    𒂗
    0.57
    \{{}\
    0.55
    𒀸
    0.54
    ᚗ
    0.54
    <unused1008>
    0.54
    រី
    0.52
    irittura
    0.52
    <unused1787>
    0.52
    <unused576>
    0.51
    WithFieldContext
    0.50
    POSITIVE LOGITS
    0.70
     K
    0.55
    imin
    0.47
     one
    0.47
    ing
    0.46
     C
    0.44
     flat
    0.43
     pros
    0.43
    sic
    0.43
    AC
    0.42
    Activations Density 0.000%

    No Known Activations