© 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. 12681
    Prev
    Next
    INDEX
    Explanations

    JSON format conversion

    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
     
    0.48
     statues
    0.47
     private
    0.46
     -
    0.45
     '
    0.45
     sukses
    0.45
    '
    0.44
    意思
    0.41
      
    0.41
    ↵↵
    0.40
    POSITIVE LOGITS
     sceGu
    0.47
    psin
    0.45
    ableConcept
    0.45
    ModelGrid
    0.45
    ackBar
    0.44
     ಕರ್
    0.44
    ковник
    0.43
    唵
    0.43
    CurrentImage
    0.42
     божомол
    0.41
    Activations Density 0.000%

    No Known Activations