© 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. 40-GEMMASCOPE-2-RES-262K
    7. 223279
    Prev
    Next
    INDEX
    Explanations

    character literals

    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
    symbol
    0.40
    symbols
    0.38
     "&#
    0.38
     '--
    0.37
    符号
    0.37
    सा
    0.35
    йна
    0.35
     Literary
    0.35
    前面的
    0.35
    би
    0.34
    POSITIVE LOGITS
     organisme
    0.40
     jugement
    0.39
     Lask
    0.39
    ╽
    0.39
     groß
    0.38
     tramite
    0.38
     lanjutkan
    0.38
    讚
    0.38
    !;
    0.37
     defiance
    0.36
    Activations Density 0.025%

    No Known Activations