© 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. 125406
    Prev
    Next
    INDEX
    Explanations

    compartments and sequences

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

    essential or basic

    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
     आंतर
    0.50
    phs
    0.47
    愉
    0.47
     nostru
    0.46
     corso
    0.45
     vores
    0.45
    初步
    0.45
    蠢
    0.45
    龕
    0.45
    國民
    0.44
    POSITIVE LOGITS
    ys
    0.49
    Circuit
    0.47
    ilmesi
    0.47
    Piece
    0.47
    Ella
    0.47
    verage
    0.46
    Segment
    0.46
    Rail
    0.46
    iz
    0.46
    ail
    0.45
    Activations Density 0.000%

    No Known Activations