© 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. 42001
    Prev
    Next
    INDEX
    Explanations

    punctuation and names

    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
     in
    0.26
    ។
    0.26
     ロー
    0.25
     that
    0.25
    .
    0.24
    that
    0.24
     banquet
    0.23
    ।
    0.23
    。
    0.23
    for
    0.23
    POSITIVE LOGITS
    ᥒ
    0.23
    ලි
    0.23
    ᴀ
    0.22
    ŗ
    0.22
    备注
    0.22
    6
    0.22
     numeros
    0.21
    ر
    0.21
    樱
    0.21
    ʟ
    0.21
    Activations Density 0.260%

    No Known Activations