© 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. 65163
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

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

    cycles, seasons, silent

    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
    *:
    0.50
     Altogether
    0.44
     ir
    0.44
     Enough
    0.41
    *,
    0.41
     magnified
    0.41
     inadequate
    0.41
     Extraordinary
    0.41
     Fuchs
    0.40
     Evidently
    0.39
    POSITIVE LOGITS
    جاتا
    0.54
    TreeView
    0.50
    鵡
    0.50
     коллеги
    0.50
    LogError
    0.49
    πομπ
    0.49
    IsMethod
    0.48
    वल
    0.48
     religiosa
    0.47
     religiosos
    0.47
    Activations Density 0.000%

    No Known Activations