© 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. 224502
    Prev
    Next
    INDEX
    Explanations

    undisclosed injury

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

    structured logging

    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
    c
    0.51
     coda
    0.48
    มาร
    0.46
    ف
    0.45
    運び
    0.43
    joined
    0.43
    S
    0.42
     də
    0.42
     kod
    0.41
    ｏ
    0.40
    POSITIVE LOGITS
    ଆ
    0.56
     dissipate
    0.53
    ασ
    0.50
    ösungen
    0.49
     Wohnung
    0.47
    слови
    0.47
     галу
    0.46
     예를
    0.46
     Алла
    0.46
    rensa
    0.45
    Activations Density 0.000%

    No Known Activations