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. 78
    Prev
    Next
    INDEX
    Explanations

    piston engine parts

    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
     roi
    -0.76
     Marsden
    -0.69
    égration
    -0.66
    跏
    -0.65
    ́
    -0.65
    čio
    -0.64
    寥
    -0.63
     Actu
    -0.63
    UTM
    -0.63
    吸引
    -0.63
    POSITIVE LOGITS
     piston
    1.56
     pistons
    1.26
     Piston
    1.20
    piston
    1.18
     rings
    1.02
     skirt
    1.00
     Pistons
    0.94
     ring
    0.94
     пор
    0.93
     skirts
    0.92
    Activations Density 0.022%

    No Known Activations