© 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. 116567
    Prev
    Next
    INDEX
    Explanations

    contact information

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

    recipe requests

    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
    cego
    0.54
    Tes
    0.49
    個
    0.49
    型
    0.46
    تي
    0.46
     nich
    0.45
    ها
    0.45
    dwelling
    0.44
    дви
    0.44
    тых
    0.44
    POSITIVE LOGITS
     Intensity
    0.45
     Intensive
    0.44
     Begin
    0.41
    *****/
    0.41
     νέα
    0.41
    enteri
    0.41
     currentTime
    0.40
     Honduras
    0.40
    agamanam
    0.40
    措施
    0.39
    Activations Density 0.000%

    No Known Activations