© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103553
    Prev
    Next
    INDEX
    Explanations

    flint and steel

    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
    ado
    0.57
    larını
    0.56
    netje
    0.56
    वीन
    0.55
    ц
    0.54
    ер
    0.54
    ni
    0.51
    lere
    0.50
    ни
    0.50
    Č
    0.50
    POSITIVE LOGITS
    睡眠
    0.46
    海洋
    0.46
    illés
    0.45
     библиотека
    0.44
    㫴
    0.41
     horarios
    0.41
    તિહાસ
    0.41
    ಸ್ತಕ
    0.41
    陵
    0.40
     মেডিকেল
    0.40
    Activations Density 0.000%

    No Known Activations