Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169834
    Prev
    Next
    INDEX
    Explanations

    explaining concepts or definitions

    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
    ছে
    0.43
     законодав
    0.43
    <0xBD>
    0.43
    Governance
    0.43
    ז
    0.43
    즈
    0.41
    FLOAT
    0.41
     sowas
    0.41
    નમાં
    0.40
    Legisl
    0.40
    POSITIVE LOGITS
    ’
    0.45
     형태
    0.45
     Hug
    0.44
     Shopify
    0.44
     ポイント
    0.43
     専用
    0.42
    atra
    0.42
     Pon
    0.42
    期货
    0.42
    MSFont
    0.41
    Activations Density 0.004%

    No Known Activations