© 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. 26452
    Prev
    Next
    INDEX
    Explanations

    parameter values

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

    sql insert values

    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
    Analyzer
    0.41
    ूरिया
    0.40
    Restriction
    0.39
    彝
    0.39
    埂
    0.39
     antelope
    0.38
    Fond
    0.38
    สภาพ
    0.38
    лери
    0.38
    Tank
    0.37
    POSITIVE LOGITS
     values
    0.50
    values
    0.49
     Values
    0.45
     valores
    0.44
    挿
    0.43
     值
    0.42
    value
    0.42
     value
    0.42
     VALUES
    0.41
    trasound
    0.41
    Activations Density 0.000%

    No Known Activations