© 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. 62576
    Prev
    Next
    INDEX
    Explanations

    suggests that

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

    suggests or implies

    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
     P
    0.79
     V
    0.78
     S
    0.74
     L
    0.73
     dari
    0.73
     D
    0.70
     was
    0.70
     B
    0.69
     för
    0.68
     Z
    0.67
    POSITIVE LOGITS
    Q
    0.94
    가능
    0.92
    ﻲ
    0.89
    й
    0.89
     possíveis
    0.86
    H
    0.85
     możliwości
    0.82
    مكان
    0.81
     posibles
    0.80
    му
    0.80
    Activations Density 0.034%

    No Known Activations