© 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. 7747
    Prev
    Next
    INDEX
    Explanations

    neutral flame

    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
     basename
    0.41
    랑
    0.41
    飒
    0.41
    ference
    0.39
    정과
    0.38
     Bacter
    0.38
     Grenoble
    0.37
    σιο
    0.37
    LetterIndex
    0.37
    ães
    0.37
    POSITIVE LOGITS
     threads
    0.46
    THREADS
    0.46
    PUT
    0.44
    ၅
    0.43
     প্রেমের
    0.43
    HUD
    0.43
     Thread
    0.42
     Threads
    0.42
    K
    0.42
    中国
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.