© 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. 32617
    Prev
    Next
    INDEX
    Explanations

    material after "**"

    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
     최대
    0.46
    arios
    0.46
     atro
    0.44
     過
    0.44
     keb
    0.44
    讯
    0.43
     kont
    0.43
     trunks
    0.43
     connectors
    0.42
     etik
    0.42
    POSITIVE LOGITS
    ên
    0.53
    們
    0.48
    掬
    0.43
    们
    0.43
     ಸಿನಿ
    0.42
    鮨
    0.41
     âg
    0.41
    とその
    0.41
     цих
    0.41
     സംഭവ
    0.41
    Activations Density 0.001%

    No Known Activations