© 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. 42979
    Prev
    Next
    INDEX
    Explanations

    control over, blues rock, God I

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

    Recovery, entry, JWT, variable

    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
    エ
    0.48
    纶
    0.48
    ブル
    0.46
    バー
    0.45
    Nicholas
    0.45
    滢
    0.43
    дже
    0.43
    ッティング
    0.43
    ヤマ
    0.43
    盧
    0.42
    POSITIVE LOGITS
    !!");
    0.47
    Finish
    0.46
    ]["
    0.44
    Logout
    0.44
    swt
    0.44
     ОБ
    0.44
     Anniversary
    0.44
     કરાવ
    0.43
     अल्ट
    0.43
     "))
    0.43
    Activations Density 0.000%

    No Known Activations