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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105954
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
    <bos>
    -1.98
     zowel
    -1.59
     Ausrüstung
    -1.39
    、【
    -1.34
     so
    -1.33
    酣
    -1.32
     tarjo
    -1.30
     chré
    -1.24
    igurumi
    -1.24
     الأش
    -1.23
    POSITIVE LOGITS
     They
    1.63
    Specific
    1.62
    龵
    1.60
    TYPES
    1.51
    {
    1.43
    当你
    1.40
     विभिन्न
    1.39
    "",
    
    1.38
    踫
    1.37
    Highly
    1.34
    Activations Density 0.014%

    No Known Activations