© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6648
    Prev
    Next
    INDEX
    Explanations

    dependencies and imports

    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
    CLUS
    0.39
    विष
    0.39
    Compl
    0.38
     plabic
    0.38
    Compounds
    0.38
    㞓
    0.38
    苷
    0.37
    Composition
    0.37
    तुर
    0.36
     gameOver
    0.36
    POSITIVE LOGITS
    ید
    0.53
     T
    0.47
    ia
    0.47
    о
    0.47
    v
    0.46
    го
    0.46
    а
    0.46
    io
    0.45
     K
    0.45
    ow
    0.44
    Activations Density 0.001%

    No Known Activations