© 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. 97236
    Prev
    Next
    INDEX
    Explanations

    artists and arts

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

    avoiding overly technical claims

    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
    rea
    0.52
     एंगल
    0.44
     rahu
    0.43
    afe
    0.43
    뱀
    0.42
    aat
    0.42
    Diagonal
    0.42
    зулта
    0.41
    REA
    0.41
    meye
    0.41
    POSITIVE LOGITS
     Stray
    0.47
     اتباع
    0.46
    影
    0.45
     Launches
    0.44
    ἱ
    0.44
     Biscuit
    0.44
     Throw
    0.43
     Broken
    0.42
     Wonder
    0.42
     কামাল
    0.42
    Activations Density 0.003%

    No Known Activations