Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8482
    Prev
    Next
    INDEX
    Explanations

    function definitions and mappings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sloveniji
    -0.96
     include
    -0.95
    含ま
    -0.87
     Adjustment
    -0.85
     incluye
    -0.82
     државе
    -0.82
    FunctionType
    -0.82
    راحل
    -0.82
    rlrl
    -0.81
     siehe
    -0.79
    POSITIVE LOGITS
    :
    3.11
     :
    2.00
    }:
    1.19
    :[
    1.19
    :……
    1.06
     mapping
    1.02
    :
    0.98
    :{
    0.98
    ︰
    0.92
    Mapping
    0.90
    Activations Density 0.034%

    No Known Activations