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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8676
    Prev
    Next
    INDEX
    Explanations

    elementary school

    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
    inger
    -0.79
     CPO
    -0.78
    CMC
    -0.77
    ylene
    -0.76
     of
    -0.76
    新聞
    -0.74
    メイン
    -0.73
     traumas
    -0.72
     様子
    -0.72
     tenth
    -0.71
    POSITIVE LOGITS
     school
    2.09
     schools
    1.73
    school
    1.60
    schools
    1.34
     sekolah
    1.34
     шко
    1.30
    学校
    1.22
     школы
    1.20
     SCHOOL
    1.13
     schoolchildren
    1.13
    Activations Density 0.018%

    No Known Activations