© 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. 69720
    Prev
    Next
    INDEX
    Explanations

    liability and legal defense

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

    altered protein function

    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
    फ
    0.50
    Night
    0.49
    Открыть
    0.48
    ،
    0.48
    UNITED
    0.47
    Fisher
    0.47
    ，
    0.46
    ف
    0.46
    βα
    0.46
    United
    0.45
    POSITIVE LOGITS
     acrob
    0.55
     septum
    0.52
     larynx
    0.52
    heiten
    0.52
     caul
    0.52
     amphithe
    0.52
     antennae
    0.51
     ça
    0.50
     trachea
    0.49
    ıyordu
    0.49
    Activations Density 0.000%

    No Known Activations