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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 198
    Prev
    Next
    INDEX
    Explanations

    right followed by direction

    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
    以上
    -0.80
    AGAIN
    -0.76
     novamente
    -0.75
     AUTHORITIES
    -0.73
    宇宙
    -0.73
     تھا
    -0.72
    Gibbs
    -0.72
     AGAIN
    -0.72
    isamment
    -0.71
    bür
    -0.71
    POSITIVE LOGITS
     right
    4.13
    right
    2.95
    Right
    2.66
     Right
    2.36
    RIGHT
    2.13
     RIGHT
    1.96
     straight
    1.66
     ngay
    1.60
     derecho
    1.56
     derecha
    1.55
    Activations Density 0.036%

    No Known Activations