© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77873
    Prev
    Next
    INDEX
    Explanations

    bigint and tinyint data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pár
    -0.71
    🏇
    -0.68
    сем
    -0.67
    Father
    -0.66
     Entscheidung
    -0.66
     Homes
    -0.66
    Survivors
    -0.65
    salam
    -0.65
    зва
    -0.64
     Mitch
    -0.64
    POSITIVE LOGITS
     Intake
    0.79
    חה
    0.78
    jian
    0.77
    ರಿ
    0.77
     mobiles
    0.76
     intake
    0.75
    geom
    0.75
     mux
    0.73
     internationally
    0.72
    nait
    0.71
    Activations Density 0.047%

    No Known Activations