© 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. 77226
    Prev
    Next
    INDEX
    Explanations

    mentions of parameters

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

    parameters: variables, learnable

    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
    ح
    0.62
    অ্যাপ
    0.57
    Economy
    0.53
     Mustangs
    0.53
    ).
    0.53
     Gators
    0.52
     Johns
    0.52
     bunnies
    0.52
    大
    0.52
    Ад
    0.52
    POSITIVE LOGITS
     парамет
    1.07
     parameter
    1.05
     Parameter
    1.05
    参数
    1.05
     paramètres
    1.01
    參數
    1.01
    Parameter
    1.00
     параметра
    0.92
    parameter
    0.91
     Param
    0.90
    Activations Density 0.048%

    No Known Activations