© 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. 170260
    Prev
    Next
    INDEX
    Explanations

    fitted oralfootball matchesmillion recordsterrorists: 1.7 million

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

    investigation of, unauthorized alteration, salad exceed

    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
    טי
    0.50
    ধির
    0.45
    ও
    0.44
    🗞
    0.44
    咳嗽
    0.43
    濺
    0.42
    ワクチン
    0.42
     DIRECT
    0.41
    しゃ
    0.41
    大数据
    0.41
    POSITIVE LOGITS
    ingt
    0.46
    alities
    0.46
     كن
    0.45
    حان
    0.45
    ers
    0.44
    Etudes
    0.44
    anda
    0.43
    é
    0.43
    anan
    0.43
    ibilit
    0.42
    Activations Density 0.001%

    No Known Activations