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. 70
    Prev
    Next
    INDEX
    Explanations

    words indicating sequence or beginning

    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
    typeout
    -0.93
    Second
    -0.92
    fiées
    -0.88
     Debut
    -0.88
     Subsequent
    -0.85
    żył
    -0.84
    ätzlich
    -0.84
    fontein
    -0.83
     eneste
    -0.79
     השני
    -0.78
    POSITIVE LOGITS
     first
    6.06
     сначала
    5.25
     primero
    5.06
    先
    4.84
     eerst
    4.72
    首先
    4.53
     først
    4.47
    まず
    4.34
     zuerst
    4.28
     ابتدا
    4.28
    Activations Density 0.010%

    No Known Activations