© 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. 139267
    Prev
    Next
    INDEX
    Explanations

    guide you or us

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

    providing guidance

    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
    ↵↵
    0.73
    prising
    0.68
     interne
    0.65
    ation
    0.64
     Indien
    0.62
     as
    0.60
     +
    0.60
    t
    0.60
    är
    0.57
     arme
    0.57
    POSITIVE LOGITS
    ガイド
    1.10
    guid
    1.01
     guidance
    0.98
     guid
    0.97
     guiding
    0.97
    guide
    0.97
    guided
    0.97
     guided
    0.92
     GUID
    0.91
     directing
    0.90
    Activations Density 0.155%

    No Known Activations