© 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. 15
    Prev
    Next
    INDEX
    Explanations

    numbers 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_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
    🧉
    0.35
    萧
    0.35
    🍥
    0.35
     时尚
    0.34
    卫生
    0.34
    ävät
    0.34
     Chủ
    0.34
    acariy
    0.33
    🍡
    0.33
     नाखून
    0.33
    POSITIVE LOGITS
    0
    0.52
     thousand
    0.49
    9
    0.47
    8
    0.47
    6
    0.45
     thousands
    0.44
    0.43
    1
    0.43
    7
    0.41
    2
    0.40
    Activations Density 0.092%

    No Known Activations