© 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. 57320
    Prev
    Next
    INDEX
    Explanations

    games, table tennis, State

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

    moving, variable, theological, density

    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
     পরিচালিত
    0.46
     Lucio
    0.45
    参与
    0.45
     Alessandro
    0.43
    芷
    0.43
    狡
    0.43
    ಿಯನ್ನು
    0.42
    生活
    0.42
     ಬಿಜೆ
    0.41
    }^\
    0.41
    POSITIVE LOGITS
     aspekt
    0.45
    COLOR
    0.42
    Interop
    0.42
     emulsions
    0.42
    텁
    0.41
    酸
    0.41
     bouillon
    0.40
     prostagland
    0.40
     tulee
    0.39
    RAW
    0.39
    Activations Density 0.000%

    No Known Activations