© 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. 162825
    Prev
    Next
    INDEX
    Explanations

    a student of facilities

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

    natural keys, code, and memory

    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
    (
    0.52
     rie
    0.51
    _
    0.49
     folly
    0.47
    )
    0.47
    GI
    0.47
    ajax
    0.47
    Close
    0.46
     racional
    0.46
    Rational
    0.46
    POSITIVE LOGITS
    쟌
    0.53
    ಟ್‌
    0.51
     ब्लूटूथ
    0.51
     Оксана
    0.50
     loài
    0.50
    ಂಟು
    0.50
     सीटों
    0.48
     ブレスレット
    0.47
    を見
    0.47
    ("|"+"
    0.47
    Activations Density 0.001%

    No Known Activations