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. 35
    Prev
    Next
    INDEX
    Explanations

    pre- words

    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
    outé
    -0.84
     scoop
    -0.81
     أبو
    -0.78
     Entsche
    -0.77
     vitaminas
    -0.76
     causas
    -0.75
     íntegra
    -0.75
    鮭
    -0.75
     bailarina
    -0.74
    itzende
    -0.73
    POSITIVE LOGITS
    预
    0.88
    ISODE
    0.82
    Pre
    0.79
    pre
    0.77
     activiteiten
    0.77
     tertentu
    0.76
    preg
    0.74
    ७
    0.74
     onPage
    0.74
    स्प
    0.73
    Activations Density 0.051%

    No Known Activations