© 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. 148092
    Prev
    Next
    INDEX
    Explanations

    market shares

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

    punctuation and 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
    ◃
    0.53
     जीवनी
    0.52
     Haag
    0.51
    '`,
    0.50
     वास्तविक
    0.49
     Alhaji
    0.48
     contraire
    0.46
    𒄀
    0.46
    iooni
    0.46
     زید
    0.46
    POSITIVE LOGITS
     oceans
    0.50
    治安
    0.47
    ру
    0.44
     betting
    0.44
    КУ
    0.43
    امي
    0.42
    таў
    0.42
     buzzing
    0.41
    она
    0.40
    약
    0.39
    Activations Density 0.001%

    No Known Activations