© 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-262K
    4. 41051
    Prev
    Next
    INDEX
    Explanations

    adding ingredients or options

    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
     L
    0.54
    -
    0.54
     es
    0.47
     boring
    0.47
     D
    0.46
     crazy
    0.46
    '
    0.45
     de
    0.45
      
    0.44
     #
    0.44
    POSITIVE LOGITS
    glRaster
    0.60
    SScript
    0.59
    的处理
    0.54
     américains
    0.53
    getBlueTeam
    0.53
    pInBuffer
    0.51
    RAchievement
    0.50
    rawData
    0.50
    CommandBuffer
    0.50
    getImageFolder
    0.50
    Activations Density 0.004%

    No Known Activations