© 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. 232340
    Prev
    Next
    INDEX
    Explanations

    buy, ads, liable, heart, ready, culture

    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
    闘
    0.52
    纷
    0.49
     후
    0.47
    ingresso
    0.45
    sville
    0.45
    受信
    0.45
    ਬ
    0.45
    ベーション
    0.45
    ონი
    0.44
    勇
    0.44
    POSITIVE LOGITS
     insulated
    0.52
     innan
    0.52
     thermometers
    0.52
     unmittel
    0.51
     casks
    0.51
     izinsuku
    0.49
     izol
    0.48
     Schweiz
    0.48
     insulate
    0.48
     windmills
    0.47
    Activations Density 0.000%

    No Known Activations