© 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. 134247
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "The"

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

    viral infection

    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
    en
    0.54
     Ingredients
    0.54
     Information
    0.52
    s
    0.52
    ;
    0.50
     Food
    0.49
     Homepage
    0.49
    ination
    0.47
     Idea
    0.47
     Resources
    0.47
    POSITIVE LOGITS
    ہوں
    0.45
    חו
    0.44
     다섯
    0.44
    쟈
    0.44
     trajetória
    0.43
    нибудь
    0.43
    값이
    0.43
     다음과
    0.42
    Ǻ
    0.42
     finit
    0.41
    Activations Density 0.000%

    No Known Activations