© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25458
    Prev
    Next
    INDEX
    Explanations

    historical eras and empires

    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
    並且
    0.43
    并且
    0.42
     foods
    0.41
     י
    0.40
     aliments
    0.39
    foods
    0.39
     indígena
    0.39
     tudo
    0.39
     enfants
    0.39
     ی
    0.38
    POSITIVE LOGITS
     nearer
    0.40
     Era
    0.39
    ydı
    0.39
    ABIL
    0.38
     era
    0.37
    BW
    0.37
     llevaba
    0.37
     during
    0.37
     DURING
    0.36
     tokom
    0.36
    Activations Density 0.019%

    No Known Activations