© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 13292
    Prev
    Next
    INDEX
    Explanations

    individual experiences and variations

    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
    ↵↵
    1.08
    ৬
    0.90
    ות
    0.88
    leq
    0.86
    シ
    0.85
     a
    0.82
    8
    0.80
    ない
    0.75
    }$
    0.74
     แต่
    0.74
    POSITIVE LOGITS
    ى
    0.89
    0
    0.76
     индивидуа
    0.75
    the
    0.70
    ور
    0.70
    are
    0.68
     склон
    0.67
     распростран
    0.67
     individuale
    0.67
    ਰ
    0.66
    Activations Density 0.029%

    No Known Activations