© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 25117
    Prev
    Next
    INDEX
    Explanations

    peak *

    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_all/layer_41_width_262k_l0_big
    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
    एंगे
    0.40
    ategory
    0.40
    黾
    0.39
    መር
    0.39
     démontrer
    0.39
    Gabriel
    0.38
     സാഹചര്യ
    0.38
    琐
    0.38
    duire
    0.38
    liminf
    0.37
    POSITIVE LOGITS
     peak
    2.33
     Peak
    1.95
     peaked
    1.95
    peak
    1.93
    Peak
    1.88
     peaking
    1.83
     peaks
    1.79
    ピーク
    1.79
     puncak
    1.70
    峰
    1.56
    Activations Density 0.003%

    No Known Activations