© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127706
    Prev
    Next
    INDEX
    Explanations

    password fields

    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
    盌
    -2.95
    轳
    -2.81
    (
    -2.59
    iffance
    -2.53
    琑
    -2.52
     asesin
    -2.45
     terrific
    -2.44
     неболь
    -2.42
    喾
    -2.39
    
    -2.39
    POSITIVE LOGITS
    .
    3.03
    <bos>
    2.81
    <i>
    2.50
     сказала
    2.47
     Erhöhung
    2.41
    ↵
    2.41
    勍
    2.38
    </b>
    2.36
    蔼
    2.33
     häufig
    2.31
    Activations Density 0.006%

    No Known Activations