© 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. 70635
    Prev
    Next
    INDEX
    Explanations

    technical commands and configurations

    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
     cadeira
    -1.53
    cadeau
    -1.53
     jiné
    -1.37
     alguns
    -1.35
    yyj
    -1.34
    युक्त
    -1.34
    ických
    -1.34
     bazı
    -1.33
    parfum
    -1.32
    tarte
    -1.30
    POSITIVE LOGITS
    了什么
    1.40
     each
    1.39
     =
    1.34
    zają
    1.27
     Each
    1.27
     After
    1.26
     As
    1.22
    );
    
    1.20
     bestätigen
    1.17
     Over
    1.15
    Activations Density 0.182%

    No Known Activations