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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 109577
    Prev
    Next
    INDEX
    Explanations

    March

    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_16_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
     ഔ
    0.57
     мод
    0.55
    ナイ
    0.52
     конфи
    0.50
     gua
    0.50
     cfg
    0.50
     М
    0.49
     erect
    0.49
     گیرد
    0.49
    ༢
    0.49
    POSITIVE LOGITS
    šo
    0.46
    शेदपुर
    0.45
    Примітки
    0.43
    有助于
    0.42
    Inset
    0.41
    aile
    0.41
     Esso
    0.41
    र्टी
    0.41
    徜
    0.41
    עות
    0.41
    Activations Density 0.000%

    No Known Activations