© 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. 30385
    Prev
    Next
    INDEX
    Explanations

    sworn to secrecy

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

    First Day of Week

    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
     Fur
    0.46
     B
    0.45
     O
    0.44
     H
    0.43
     Bela
    0.41
     L
    0.41
    O
    0.40
     Pfer
    0.40
     N
    0.39
     K
    0.39
    POSITIVE LOGITS
     exemplify
    0.47
    SwitchCompat
    0.45
    lyPlugin
    0.44
     exemplifies
    0.44
     accommodate
    0.43
    gcash
    0.43
    ByMerging
    0.42
    tfine
    0.42
    只限平日
    0.42
    Ỡ
    0.42
    Activations Density 0.000%

    No Known Activations