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. 59
    Prev
    Next
    INDEX
    Explanations

    Cell and biological terms

    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
    Freq
    -0.73
     trova
    -0.72
     intracranial
    -0.71
     voisins
    -0.71
    igner
    -0.71
     Unión
    -0.70
     zio
    -0.69
     lele
    -0.69
    typeOf
    -0.69
     кафе
    -0.68
    POSITIVE LOGITS
     parame
    1.06
     osmosis
    0.99
     transpiration
    0.95
     Specialization
    0.93
     respiration
    0.87
     specialization
    0.85
     vacu
    0.85
     vaccines
    0.84
     prokary
    0.83
     mitosis
    0.81
    Activations Density 0.026%

    No Known Activations