© 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. 47547
    Prev
    Next
    INDEX
    Explanations

    or equal to

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

    logical OR operator

    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
    شاه
    0.54
     ניתן
    0.51
    祚
    0.50
     тільки
    0.48
     خمسه
    0.48
     stave
    0.47
    𒄑
    0.47
    𝑌
    0.47
    Strafpunkte
    0.47
    ONLY
    0.46
    POSITIVE LOGITS
    acles
    0.50
    ald
    0.50
    ignal
    0.49
    amb
    0.48
    leans
    0.47
    ings
    0.47
    ura
    0.45
    hooks
    0.45
    ader
    0.44
    ients
    0.44
    Activations Density 0.003%

    No Known Activations