© 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. 31-GEMMASCOPE-2-RES-65K
    7. 5849
    Prev
    Next
    INDEX
    Explanations

    code keywords and identifiers

    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_65k_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
    AI
    0.43
    ⁻
    0.41
    EN
    0.40
     don
    0.39
     تلف
    0.39
    .
    0.39
    GE
    0.38
    OR
    0.38
     기
    0.37
    ла
    0.37
    POSITIVE LOGITS
    ជាមួយ
    0.45
    ovaných
    0.43
    ມີ
    0.43
     संवेदनशील
    0.43
    Avec
    0.43
    mment
    0.42
     nerveux
    0.41
     vgl
    0.41
    overlaps
    0.41
    ঞ্ছ
    0.40
    Activations Density 0.332%

    No Known Activations