© 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. 61198
    Prev
    Next
    INDEX
    Explanations

    flexible contrast

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

    starting a new

    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
    a
    0.52
    s
    0.49
    韵
    0.48
    sales
    0.48
     والح
    0.47
    ند
    0.46
     عندما
    0.46
    ק
    0.45
    shell
    0.45
     *,
    0.45
    POSITIVE LOGITS
    atility
    0.48
     cornerback
    0.47
     informally
    0.47
    ibility
    0.44
    ockeys
    0.44
    ELS
    0.44
     पदार्थों
    0.43
    ization
    0.43
    ėl
    0.42
     ĝi
    0.42
    Activations Density 0.000%

    No Known Activations