© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180489
    Prev
    Next
    INDEX
    Explanations

    finding real meaning

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

    specific numbers or locations

    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
    Strawberry
    0.50
    LLI
    0.47
    Assignment
    0.46
    o
    0.46
    富
    0.46
    PCA
    0.44
     Α
    0.44
    ان
    0.44
    Просе
    0.44
    centes
    0.44
    POSITIVE LOGITS
     zei
    0.52
     gamepad
    0.52
     zone
    0.51
     tủ
    0.51
     film
    0.49
     folgender
    0.49
     fence
    0.48
     മേഖല
    0.48
     gaze
    0.47
     nakon
    0.47
    Activations Density 0.001%

    No Known Activations