© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54160
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    tizing
    -0.75
     penn
    -0.73
     calc
    -0.73
    deutschland
    -0.71
     Cats
    -0.70
    料金
    -0.70
    akal
    -0.69
    орты
    -0.66
    makaian
    -0.66
    Buck
    -0.65
    POSITIVE LOGITS
     Newborn
    0.79
    ("}");
    0.71
    werb
    0.67
    嚎
    0.67
    踰
    0.66
     Zyg
    0.66
    툭
    0.66
     уго
    0.66
    冲
    0.66
    душка
    0.66
    Activations Density 0.042%

    No Known Activations