© 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. 76919
    Prev
    Next
    INDEX
    Explanations

    digital ledger

    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
    s
    0.57
     is
    0.51
     spect
    0.50
    0.48
     .
    0.46
     HTML
    0.46
    ä
    0.46
     are
    0.45
    OF
    0.45
    LOG
    0.45
    POSITIVE LOGITS
     похађа
    0.51
     Idani
    0.51
    зий
    0.51
     Kxa
    0.51
    iyaç
    0.47
    𝗯
    0.47
     ня
    0.46
    ônia
    0.46
     poda
    0.46
     동일
    0.46
    Activations Density 0.002%

    No Known Activations