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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12284
    Prev
    Next
    INDEX
    Explanations

    length after parenthesis

    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_16k_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
     employability
    0.50
    𝒃
    0.48
    pection
    0.47
     عنہ
    0.47
     ẹ
    0.47
     dịp
    0.46
     pedibusque
    0.46
    aterials
    0.45
    গ্রস্ত
    0.45
    ྭ
    0.45
    POSITIVE LOGITS
    2
    0.43
    сі
    0.41
    си
    0.41
    OS
    0.41
     ката
    0.40
     objectif
    0.40
     международ
    0.39
    狼
    0.39
    лі
    0.39
     konstant
    0.39
    Activations Density 0.011%

    No Known Activations