© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135993
    Prev
    Next
    INDEX
    Explanations

    contact for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    0.50
    >
    0.47
    DETAIL
    0.40
    ള്
    0.39
    DB
    0.39
    DTO
    0.39
    ätzlich
    0.39
    );
    0.39
    Font
    0.38
    Img
    0.37
    POSITIVE LOGITS
     placards
    0.47
     grams
    0.46
     caution
    0.45
    ної
    0.45
     الفيز
    0.44
     cobbl
    0.44
    𝓊
    0.44
     célé
    0.44
     कैंसर
    0.44
     blackberry
    0.44
    Activations Density 0.004%

    No Known Activations