© 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. 240340
    Prev
    Next
    INDEX
    Explanations

    structural builds, organic foods, or craving

    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
    תר
    0.54
    ライダー
    0.47
     আট
    0.45
     ಯ
    0.45
    "{@
    0.45
    균
    0.45
    Flare
    0.44
    TIMEOUT
    0.44
    ソフトウェア
    0.44
     inhale
    0.43
    POSITIVE LOGITS
    Meesho
    0.44
    فرج
    0.43
    ája
    0.42
    auti
    0.42
    orty
    0.42
    筝
    0.42
    apek
    0.42
    fg
    0.41
    ්‍
    0.41
    ྛ
    0.41
    Activations Density 0.001%

    No Known Activations