© 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. 122911
    Prev
    Next
    INDEX
    Explanations

    city, survivors, car, Manhattan

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

    try to make metry to get metry to breaktrying to find

    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
    an
    0.64
    i
    0.58
    p
    0.53
    two
    0.50
    his
    0.48
    c
    0.47
    K
    0.47
    지
    0.47
    ivo
    0.47
    re
    0.46
    POSITIVE LOGITS
     provoked
    0.48
     బిల్
    0.46
     errorCode
    0.46
     سل
    0.44
     リン
    0.44
     univariate
    0.44
     uncovering
    0.43
     அக
    0.43
     warrantless
    0.43
     зи
    0.43
    Activations Density 0.000%

    No Known Activations