© 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. 38444
    Prev
    Next
    INDEX
    Explanations

    calculate remainder subtract

    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
    任務
    0.45
    浐
    0.44
    pector
    0.44
    逐漸
    0.44
    動画
    0.42
    方法は
    0.41
    ང
    0.41
     escala
    0.41
    ниях
    0.41
    ．
    0.41
    POSITIVE LOGITS
    czną
    0.45
     ก
    0.41
     Impression
    0.40
     Sed
    0.39
     무게
    0.39
     softly
    0.39
     tann
    0.39
    sed
    0.39
     Galleria
    0.38
     impression
    0.38
    Activations Density 0.000%

    No Known Activations