© 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. 54296
    Prev
    Next
    INDEX
    Explanations

    other options or alternatives

    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
     to
    0.60
    s
    0.57
    sim
    0.52
     a
    0.47
     handles
    0.46
    substitution
    0.45
     spaghetti
    0.44
     scratches
    0.42
    t
    0.42
     projections
    0.42
    POSITIVE LOGITS
    ιδ
    0.52
     ブランド
    0.52
     約
    0.51
     每
    0.51
     ਬ
    0.50
    idunt
    0.50
     整
    0.49
    ijų
    0.49
     பற்றிய
    0.49
    జే
    0.49
    Activations Density 0.001%

    No Known Activations