© 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-262K
    7. 5311
    Prev
    Next
    INDEX
    Explanations

    variable and parameter names

    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_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
     typographical
    0.16
    <0xF3>
    0.16
    radle
    0.16
    
    0.16
    ప్పుడు
    0.15
     %``
    0.15
    Bringing
    0.15
     refracting
    0.15
    taking
    0.15
    <0xE0>
    0.15
    POSITIVE LOGITS
     filename
    0.23
     tempList
    0.20
     hogi
    0.20
    StartTime
    0.19
     username
    0.19
     price
    0.19
     userService
    0.19
     apiClient
    0.19
    objPHPExcel
    0.19
     emberek
    0.19
    Activations Density 0.215%

    No Known Activations