© 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. 7136
    Prev
    Next
    INDEX
    Explanations

    used in everything

    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
    uating
    0.46
    ้า
    0.46
    χου
    0.46
    蕾
    0.45
    ëm
    0.44
    ští
    0.43
    aré
    0.43
    肉
    0.42
    都是
    0.42
    heits
    0.42
    POSITIVE LOGITS
    дцать
    0.43
    \,
    0.43
    kw
    0.42
     الموجود
    0.42
    ക്കി
    0.42
     வகைகள்
    0.41
    సక్తి
    0.40
     dide
    0.40
     understandings
    0.38
     অ্যান্টি
    0.38
    Activations Density 0.010%

    No Known Activations