© 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. 31-GEMMASCOPE-2-RES-262K
    7. 109037
    Prev
    Next
    INDEX
    Explanations

    component level

    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_31_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
     راجس
    0.55
     อ่า
    0.54
     పరీక్ష
    0.51
     ሌሎች
    0.50
    UpdateChoice
    0.49
     معنات
    0.48
    überkü
    0.47
    贛
    0.47
     ニュー
    0.46
     يكون
    0.46
    POSITIVE LOGITS
     pp
    0.52
     per
    0.48
     Tec
    0.46
     of
    0.45
     PP
    0.45
     Alkali
    0.44
     semula
    0.43
     Authentic
    0.43
     Neighborhood
    0.43
     Dic
    0.43
    Activations Density 0.000%

    No Known Activations