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. 8144
    Prev
    Next
    INDEX
    Explanations

    specific codes or numbers

    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
    Word
    -0.68
    angle
    -0.68
    Orth
    -0.68
    Faites
    -0.68
     bài
    -0.68
    replace
    -0.66
    Angle
    -0.65
    itors
    -0.64
     Camila
    -0.64
    werker
    -0.63
    POSITIVE LOGITS
    wasi
    0.73
    Relevance
    0.68
    prov
    0.68
    MIG
    0.68
    Gul
    0.67
    Santi
    0.66
     ГУ
    0.65
    зор
    0.65
    immunity
    0.65
    Arist
    0.65
    Activations Density 0.068%

    No Known Activations