© 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. 252136
    Prev
    Next
    INDEX
    Explanations

    can return

    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
    ၽ
    0.51
    राज्यपाल
    0.45
    Maharashtra
    0.44
    yank
    0.43
    Những
    0.42
    Pumpkin
    0.41
    Kf
    0.41
    Punjab
    0.40
    Funny
    0.40
    Quantitative
    0.40
    POSITIVE LOGITS
     大学
    0.50
     በሚ
    0.48
     Ibu
    0.47
     commencing
    0.47
     с
    0.46
     Leon
    0.46
     يتم
    0.45
     Micros
    0.45
     Laure
    0.44
     Courts
    0.44
    Activations Density 0.000%

    No Known Activations