© 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. 19044
    Prev
    Next
    INDEX
    Explanations

    telephone numbers

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

    eight common

    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
    ب
    0.83
    ح
    0.71
    AND
    0.66
    其他
    0.65
    t
    0.65
    HAN
    0.63
    bos
    0.62
    র
    0.62
    )}
    0.62
    >
    0.61
    POSITIVE LOGITS
    ння
    0.89
    า
    0.84
    ли
    0.81
    жа
    0.75
    ло
    0.72
     They
    0.71
     CU
    0.70
    ं
    0.70
    ния
    0.66
     breezy
    0.65
    Activations Density 0.111%

    No Known Activations