© 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. 196623
    Prev
    Next
    INDEX
    Explanations

    neighbor, contents, product, hospital, assist, sponsorship

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

    curly braces `{}`

    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
    ક્રિયા
    0.50
    鰱
    0.49
    Direction
    0.48
    見て
    0.48
     কোর্স
    0.47
    CK
    0.46
    তাদের
    0.46
    蛩
    0.46
     হয়ে
    0.46
    镞
    0.45
    POSITIVE LOGITS
    abbati
    0.52
    astos
    0.47
    allas
    0.46
    addo
    0.46
    illery
    0.46
    </h5>
    0.46
    uger
    0.45
    anches
    0.45
    ile
    0.44
    ached
    0.44
    Activations Density 0.001%

    No Known Activations