© 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. 67712
    Prev
    Next
    INDEX
    Explanations

    only the best or simple solutions

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

    lists, bullet points, or structure

    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
     మరింత
    0.51
    𝖚
    0.48
    ribly
    0.48
     വെ
    0.47
    ចុ
    0.47
    setColor
    0.46
     sichtbar
    0.46
    >/</
    0.46
     ακόμα
    0.46
    POSITIVE LOGITS
     Demonstr
    0.51
     demonstrable
    0.46
     Admit
    0.45
     constants
    0.44
     MSc
    0.43
     Enthusi
    0.43
     GCSE
    0.43
     Fract
    0.43
     Faculties
    0.43
     Inter
    0.42
    Activations Density 0.000%

    No Known Activations