© 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. 159221
    Prev
    Next
    INDEX
    Explanations

    strength dimensional

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

    technical or academic discourse

    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
    lever
    0.46
    ></
    0.43
    interrupt
    0.43
     หยุด
    0.43
    vertical
    0.43
    ='
    0.42
     maaf
    0.41
    >,
    0.41
    rectangle
    0.40
    STOP
    0.40
    POSITIVE LOGITS
    тат
    0.52
     профессор
    0.50
     કરોડ
    0.49
    荿
    0.47
     spectrosc
    0.46
     elucid
    0.46
     ಕು
    0.46
    ških
    0.46
     квітня
    0.46
     avanzada
    0.46
    Activations Density 0.000%

    No Known Activations