© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1844
    Prev
    Next
    INDEX
    Explanations

    fill half or entire

    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
    フィン
    0.47
     ხელისუფლების
    0.46
    kowania
    0.39
     সভ্যতা
    0.38
     интенсив
    0.37
    cenia
    0.37
    绪
    0.37
     مرک
    0.37
     openly
    0.36
    ム
    0.36
    POSITIVE LOGITS
     filling
    1.33
     fill
    1.27
    Fill
    1.27
     fills
    1.27
    Filling
    1.27
     Fill
    1.26
    filling
    1.23
     Filling
    1.23
    fill
    1.19
     запол
    1.16
    Activations Density 0.019%

    No Known Activations