© 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. 128922
    Prev
    Next
    INDEX
    Explanations

    location and action

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

    words followed by punctuation

    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
    확
    0.47
    ỉ
    0.44
    ജന
    0.44
    եռ
    0.44
    껐
    0.44
    ァ
    0.44
    acional
    0.42
    味料
    0.42
    ắp
    0.42
    функциона
    0.42
    POSITIVE LOGITS
     Agricultural
    0.51
     Election
    0.49
     NOR
    0.49
     Ordnance
    0.49
     gegründet
    0.48
     kust
    0.48
     AER
    0.48
     kro
    0.47
     ゴ
    0.47
     genom
    0.47
    Activations Density 0.002%

    No Known Activations