© 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. 198212
    Prev
    Next
    INDEX
    Explanations

    hysterics"

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

    simplifies or describes

    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
     şekilde
    0.45
     verlie
    0.45
     z
    0.44
     রেজ
    0.44
     fuss
    0.44
     pratica
    0.43
     einzelnen
    0.42
     형식
    0.42
     Lucio
    0.42
     вигляді
    0.42
    POSITIVE LOGITS
    FFEE
    0.45
    ょう
    0.44
    ೂರು
    0.44
    ARO
    0.43
    包
    0.43
    ُول
    0.43
    ْل
    0.42
    Cors
    0.42
    THING
    0.42
    UNT
    0.40
    Activations Density 0.002%

    No Known Activations