© 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. 123290
    Prev
    Next
    INDEX
    Explanations

    actor Oscar

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

    predictive weather modeling

    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
    _
    0.69
    A
    0.58
    ↵
    0.57
    "
    0.57
     +
    0.53
    )$
    0.52
     terminology
    0.52
    D
    0.52
    '
    0.50
     ")
    0.49
    POSITIVE LOGITS
    ते
    0.52
     పలు
    0.52
     ünivers
    0.52
     науш
    0.52
     బల
    0.50
     इस्तीफा
    0.49
     социально
    0.49
     ఆర్థిక
    0.49
     Ausnahme
    0.49
     triángulos
    0.48
    Activations Density 0.000%

    No Known Activations