© 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-262K
    7. 3373
    Prev
    Next
    INDEX
    Explanations

    companies, investment, licensing

    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_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
     Jesuit
    0.49
    𝓐
    0.46
    보
    0.46
    nią
    0.45
     Goo
    0.45
    म
    0.44
    চ্ছিলাম
    0.44
     BOOK
    0.43
    ע
    0.43
     इंत
    0.43
    POSITIVE LOGITS
    ел
    0.45
     identificación
    0.42
    ន
    0.41
     ingest
    0.41
     семей
    0.40
    ığınız
    0.40
     hábitos
    0.39
     jednak
    0.38
     интеллектуа
    0.38
     émotion
    0.38
    Activations Density 0.001%

    No Known Activations