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. 227
    Prev
    Next
    INDEX
    Explanations

    IEEE 802

    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
     USB
    -0.74
    onesa
    -0.73
     недвижи
    -0.71
     堀
    -0.71
    激情
    -0.71
    skaya
    -0.69
     القرار
    -0.68
     pudieran
    -0.68
    허
    -0.68
    FACT
    -0.67
    POSITIVE LOGITS
     Fire
    1.16
    Fire
    1.06
     fire
    0.95
     FIRE
    0.83
    fire
    0.82
    FIRE
    0.79
     Target
    0.76
    igration
    0.73
    高速
    0.73
     Firestone
    0.73
    Activations Density 0.028%

    No Known Activations