© 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. 31-GEMMASCOPE-2-RES-65K
    7. 316
    Prev
    Next
    INDEX
    Explanations

    many exclamation marks

    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
    টি
    0.28
     tuple
    0.27
     CII
    0.26
     correspondiente
    0.25
     flowchart
    0.25
    i
    0.25
    fgets
    0.24
    ){
    0.24
     snugly
    0.24
     correspondingly
    0.24
    POSITIVE LOGITS
    Countryside
    0.27
    Hundred
    0.24
    лянчук
    0.23
    ्वे
    0.23
    Hundreds
    0.22
    Histoire
    0.22
    ुस्तान
    0.22
     धमाल
    0.21
     unapolog
    0.21
    沔
    0.21
    Activations Density 0.013%

    No Known Activations