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. 20
    Prev
    Next
    INDEX
    Explanations

    game cheat codes

    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
    RectangleBorder
    -0.83
    éticos
    -0.80
     these
    -0.80
     ઉ
    -0.80
     estos
    -0.78
    roben
    -0.78
    handleDelete
    -0.78
     creatividad
    -0.78
     queste
    -0.77
    estos
    -0.76
    POSITIVE LOGITS
    phile
    0.82
     selben
    0.78
     biała
    0.77
    rochie
    0.76
    veer
    0.74
     STATISTICS
    0.73
    ulongan
    0.73
    zando
    0.73
    etheless
    0.72
     klachten
    0.72
    Activations Density 0.111%

    No Known Activations