© 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. 244131
    Prev
    Next
    INDEX
    Explanations

    IUCN Red List status

    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
    ඛ
    0.48
     namely
    0.47
     délic
    0.47
     entschieden
    0.47
    plein
    0.45
    пі
    0.45
     Contempor
    0.45
     subplot
    0.44
     nämlich
    0.44
    ้วน
    0.44
    POSITIVE LOGITS
    ५
    0.46
    IGNO
    0.45
    Dx
    0.44
    すら
    0.44
    ૨
    0.43
    agency
    0.43
    ४
    0.42
    АТ
    0.42
    IGATION
    0.42
    5
    0.42
    Activations Density 0.000%

    No Known Activations