© 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. 116157
    Prev
    Next
    INDEX
    Explanations

    German, Korean, or academic terms

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

    boolean query clauses (`must`, `should`)

    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
     Executives
    0.53
     готови
    0.50
    玠
    0.48
    惣
    0.48
     सशस्त्र
    0.47
    Executives
    0.46
    邕
    0.46
     Liberties
    0.46
    Gameplay
    0.45
     राजधानी
    0.44
    POSITIVE LOGITS
     forsk
    0.53
     cl
    0.51
    νή
    0.48
     Schwe
    0.47
     천
    0.47
    uis
    0.46
     tha
    0.45
     비용
    0.44
     reg
    0.44
     Schüler
    0.44
    Activations Density 0.000%

    No Known Activations