© 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. 104825
    Prev
    Next
    INDEX
    Explanations

    procedure and foreclosure

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

    scenario and task instructions

    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
    же
    0.47
     Clutch
    0.46
     Presses
    0.46
     Seeking
    0.45
     Grimes
    0.45
     Constance
    0.45
    s
    0.44
     Константи
    0.43
     Easier
    0.42
     Como
    0.42
    POSITIVE LOGITS
    檯
    0.46
    ्रो
    0.46
     transfected
    0.45
    クロマト
    0.45
    <unused727>
    0.45
    ホルダー
    0.44
    ใต้
    0.44
     বাধা
    0.44
     органов
    0.44
     benefitted
    0.44
    Activations Density 0.001%

    No Known Activations