© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2369
    Prev
    Next
    INDEX
    Explanations

    things people like

    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_40_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
     Babylonian
    0.36
     क्रॉप
    0.34
     dispositivo
    0.34
     Lesson
    0.33
     washes
    0.33
     Keyword
    0.33
     szükséges
    0.33
    🔗
    0.33
    発生
    0.32
     حفاظ
    0.32
    POSITIVE LOGITS
     music
    0.86
     музыки
    0.85
     música
    0.81
     photography
    0.77
     muziek
    0.76
     музыку
    0.74
    音乐
    0.74
     음악
    0.73
     موسیقی
    0.72
     musique
    0.72
    Activations Density 0.043%

    No Known Activations