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-65K
    4. 2508
    Prev
    Next
    INDEX
    Explanations

    resolve to taken card

    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
    rag
    0.30
     बढ़कर
    0.30
    คอง
    0.29
    opra
    0.29
    Reflection
    0.29
    Becoming
    0.29
     prosa
    0.28
    ³
    0.28
    ṇ
    0.28
    óz
    0.28
    POSITIVE LOGITS
     Прави
    0.30
     دارو
    0.29
    ष्टिक
    0.28
    istosoma
    0.28
     طريق
    0.28
     прави
    0.27
     щи
    0.27
     STATE
    0.26
     جنيه
    0.26
    ການ
    0.26
    Activations Density 0.000%

    No Known Activations