Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7796
    Prev
    Next
    INDEX
    Explanations

    older community posts

    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
    精力
    -0.77
    ='';
    
    -0.75
    avier
    -0.73
    乓
    -0.72
    四十
    -0.72
    ÊNCIAS
    -0.71
    五十
    -0.71
     discerning
    -0.71
     copyrighted
    -0.70
     puncture
    -0.69
    POSITIVE LOGITS
     Community
    1.38
    community
    1.31
    Community
    1.27
     community
    1.23
     COMMUNITY
    1.20
    COMMUNITY
    1.13
     forum
    1.08
    Forum
    1.03
    forum
    1.02
     comunidad
    1.00
    Activations Density 0.046%

    No Known Activations