© 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. 32814
    Prev
    Next
    INDEX
    Explanations

    technical terms and calculations

    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
    ja
    0.52
    もし
    0.47
    و
    0.46
    made
    0.45
    :
    0.45
    َ
    0.44
    漢字
    0.43
    styles
    0.43
    ं
    0.42
    送料
    0.42
    POSITIVE LOGITS
     prêt
    0.52
     organelles
    0.52
     rooft
    0.52
    onActivityResult
    0.51
    aní
    0.51
     martini
    0.51
    <unused1882>
    0.51
    überkü
    0.50
    aconda
    0.50
     humili
    0.50
    Activations Density 0.000%

    No Known Activations