© 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. 216348
    Prev
    Next
    INDEX
    Explanations

    foreign language and place names

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

    equipment case, actual written, wind shear

    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
    enum
    0.50
     bia
    0.45
    alay
    0.44
    ()));
    0.43
    ափ
    0.42
     Turf
    0.40
     위하여
    0.40
     free
    0.40
     seme
    0.40
     BMP
    0.40
    POSITIVE LOGITS
    訪問
    0.46
    știg
    0.46
    Frankreich
    0.43
    フランス
    0.43
     ઘટના
    0.43
     entrevistas
    0.43
    ט
    0.42
     Fiona
    0.42
     manchmal
    0.42
     Facultad
    0.41
    Activations Density 0.000%

    No Known Activations