© 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-65K
    7. 907
    Prev
    Next
    INDEX
    Explanations

    `/` followed by `ry`

    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_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
    കും
    0.26
    鄔
    0.24
    ↵↵↵↵↵↵↵↵↵↵↵
    0.24
    Wedgwood
    0.23
    鄴
    0.22
    Toilet
    0.22
     tumultuous
    0.22
    創造
    0.22
     incontinence
    0.22
    🔷
    0.22
    POSITIVE LOGITS
    desPort
    0.28
    iaz
    0.27
     hamming
    0.27
    RatingDiff
    0.26
     privaten
    0.25
     teamTable
    0.24
     thisobject
    0.24
     dwRes
    0.24
    ia
    0.24
     умолчанию
    0.24
    Activations Density 2.350%

    No Known Activations