© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 744
    Prev
    Next
    INDEX
    Explanations

    scientific notation with parentheses

    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_10/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
     sumamente
    -1.50
     бассей
    -1.47
     desecha
    -1.45
     adhesivo
    -1.45
     extremamente
    -1.44
     DevComponents
    -1.38
     recibiendo
    -1.38
     наших
    -1.38
    ?’
    -1.38
    auxite
    -1.35
    POSITIVE LOGITS
     Compared
    1.33
     during
    1.32
    dieron
    1.30
     nowa
    1.29
    を使用した
    1.27
     (
    1.27
    炻
    1.23
    Warum
    1.23
     نادي
    1.23
    льзя
    1.22
    Activations Density 0.005%

    No Known Activations