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. 8032
    Prev
    Next
    INDEX
    Explanations

    bible book names

    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
    ->$
    -1.09
     везе
    -0.96
     oficial
    -0.94
     ModelAndView
    -0.94
     sulit
    -0.93
     нарушения
    -0.92
     инфек
    -0.90
    Other
    -0.89
    暎
    -0.87
     dégustation
    -0.86
    POSITIVE LOGITS
     Luke
    1.14
     Judges
    1.08
    Judges
    0.95
     Acts
    0.90
    RECT
    0.90
    increments
    0.86
    isted
    0.85
     ibid
    0.85
    Animate
    0.84
     kanskje
    0.84
    Activations Density 0.008%

    No Known Activations