© 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. 5013
    Prev
    Next
    INDEX
    Explanations

    academic fields and genres

    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
     বৈশিষ্ট্য
    0.42
     наличии
    0.38
     cancerous
    0.38
     用
    0.37
    SourceName
    0.37
     вершины
    0.37
     পোশাক
    0.37
     fullness
    0.36
    盏
    0.36
     наличие
    0.36
    POSITIVE LOGITS
     sociology
    0.46
     psychiatry
    0.45
     anthropology
    0.44
     matematik
    0.42
     linguistics
    0.42
     neurology
    0.40
     epistemology
    0.40
     feminism
    0.39
     thermodynamics
    0.38
     jurisprudence
    0.38
    Activations Density 0.439%

    No Known Activations