© 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. 248625
    Prev
    Next
    INDEX
    Explanations

    developing website collection

    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
    ポケモン
    0.53
     McEl
    0.51
    ེ་
    0.50
    見積
    0.47
    大きい
    0.46
    ステージ
    0.46
     mPreview
    0.46
    ",[(
    0.46
    برای
    0.45
    EnglishMarks
    0.45
    POSITIVE LOGITS
     abstra
    0.53
     uden
    0.52
    ed
    0.50
    abi
    0.50
     liquides
    0.49
    es
    0.49
     kræ
    0.49
    loose
    0.48
    loos
    0.48
    i
    0.48
    Activations Density 0.000%

    No Known Activations