© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49162
    Prev
    Next
    INDEX
    Explanations

    problems, questions, clarification

    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
     
    0.49
     Japan
    0.45
     two
    0.45
     very
    0.44
     an
    0.43
     Australia
    0.42
     name
    0.41
    www
    0.41
     a
    0.40
     decade
    0.40
    POSITIVE LOGITS
     problema
    0.47
     planificación
    0.47
     questões
    0.47
     تحليل
    0.47
     cuestiones
    0.47
    蒎
    0.47
     compreensão
    0.46
    🚺
    0.45
     comprensión
    0.44
    OrderFlight
    0.44
    Activations Density 0.003%

    No Known Activations