© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13781
    Prev
    Next
    INDEX
    Explanations

    programming nouns followed by code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steins
    0.40
    וא
    0.38
    砖
    0.37
    器材
    0.37
    毫米
    0.37
    ओसी
    0.37
    ጊዜ
    0.36
     최대한
    0.36
    ኦ
    0.35
    ਾਮ
    0.35
    POSITIVE LOGITS
    <unused2009>
    0.44
    QtGui
    0.40
    ource
    0.38
    afe
    0.38
    lice
    0.38
     Sagan
    0.38
    printf
    0.38
    pèce
    0.38
    aves
    0.37
    zzle
    0.37
    Activations Density 0.043%

    No Known Activations