© 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. 81446
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
    ?
    0.55
    0.48
     գ
    0.48
    Harm
    0.48
    P
    0.47
    G
    0.47
    Har
    0.46
     Thr
    0.45
    W
    0.45
     w
    0.45
    POSITIVE LOGITS
    lyPlugin
    0.52
    Соцмережа
    0.52
     carers
    0.50
    FBSDKInternal
    0.48
    ೋಜನ
    0.48
    녓
    0.48
    Ნ
    0.47
    ızı
    0.47
    <>());
    0.46
    ുകള്‍
    0.46
    Activations Density 0.007%

    No Known Activations