© 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. 126020
    Prev
    Next
    INDEX
    Explanations

    too short, too close, real close

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

    depends heavily on context

    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
    0
    0.51
     نصف
    0.46
     سعر
    0.45
     Sea
    0.45
    -
    0.45
    green
    0.45
     gennaio
    0.44
     Farms
    0.44
     Revis
    0.44
    el
    0.44
    POSITIVE LOGITS
    полнение
    0.51
    ᖏ
    0.49
     rencana
    0.49
     Федерации
    0.48
    вае
    0.47
     RUDDER
    0.47
    ())).
    0.46
    वेलकम
    0.46
    чность
    0.46
    பட
    0.46
    Activations Density 0.000%

    No Known Activations