© 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. 100136
    Prev
    Next
    INDEX
    Explanations

    random number and item generation

    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
    在
    0.67
    يه
    0.61
     في
    0.58
     தேவ
    0.58
     in
    0.54
    gian
    0.53
     μπορεί
    0.52
    もら
    0.50
     मेहन
    0.48
    γμα
    0.48
    POSITIVE LOGITS
    ä
    0.72
    as
    0.60
    OL
    0.59
    ವಾಗಿ
    0.57
    RI
    0.55
     aswell
    0.51
    ore
    0.51
    RO
    0.51
    EN
    0.50
    到的
    0.49
    Activations Density 0.036%

    No Known Activations