© 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. 10208
    Prev
    Next
    INDEX
    Explanations

    errors early, defined, least

    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
    ל
    0.60
    א
    0.53
    ס
    0.51
    ז
    0.49
    WHAT
    0.47
    يني
    0.47
    Prz
    0.46
    شوف
    0.45
     shaw
    0.45
    ي
    0.44
    POSITIVE LOGITS
    un
    0.45
     любых
    0.44
     ditth
    0.42
    ont
    0.42
     مداخل
    0.41
     habilidad
    0.41
     attham
    0.40
    ностях
    0.40
     Hindi
    0.40
     Scandinavia
    0.39
    Activations Density 0.002%

    No Known Activations