© 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. 44204
    Prev
    Next
    INDEX
    Explanations

    . of the to -> Which from off write

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

    numbers and punctuation

    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
     سیاسی
    0.48
    ظ
    0.47
    经营
    0.46
    政治
    0.45
     ಕೆಲಸ
    0.44
     politiques
    0.44
    یده
    0.42
    谀
    0.42
     فروش
    0.42
    商业
    0.42
    POSITIVE LOGITS
    8
    0.63
     two
    0.59
     that
    0.59
    4
    0.57
     eight
    0.57
     matchup
    0.57
     transcriptome
    0.56
     ChIP
    0.56
     data
    0.55
    data
    0.54
    Activations Density 0.000%

    No Known Activations