© 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. 107109
    Prev
    Next
    INDEX
    Explanations

    health and danger

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

    curiosity and clues

    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
     tossed
    0.55
     Chauhan
    0.51
    O
    0.49
     tabulated
    0.49
    <table>
    0.48
     underlined
    0.47
     subray
    0.47
    E
    0.46
    y
    0.45
    ι
    0.45
    POSITIVE LOGITS
    眠
    0.47
    មិន
    0.45
     hierarchies
    0.44
     மாசுபா
    0.43
    ارية
    0.43
     architectures
    0.42
    arene
    0.41
    ަމ
    0.40
    ارق
    0.40
    pare
    0.39
    Activations Density 0.000%

    No Known Activations