© 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. 6864
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ASHI
    0.44
    しながら
    0.40
    ashi
    0.40
    ='%
    0.39
    shi
    0.39
    ры
    0.38
    ］
    0.38
    اشی
    0.36
    दूर
    0.36
     практика
    0.36
    POSITIVE LOGITS
    DESCRIPTION
    0.52
    COMPUTER
    0.46
    우스
    0.45
    REGISTER
    0.44
    훔
    0.44
    PRODUCT
    0.44
     DESCRIPTION
    0.44
    Catalogue
    0.44
    BatchNorm
    0.43
    Register
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.