© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60351
    Prev
    Next
    INDEX
    Explanations

    legal notices and file contexts

    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
    azure
    -0.82
     knex
    -0.77
     darbo
    -0.68
     darb
    -0.67
     termo
    -0.67
     EMPTY
    -0.66
     tarif
    -0.66
    chang
    -0.66
    knex
    -0.65
     buku
    -0.64
    POSITIVE LOGITS
    ぐるみ
    0.78
    Wr
    0.73
     hypertrophy
    0.69
     schneiden
    0.68
    DAA
    0.67
    ドゥ
    0.67
    いぐるみ
    0.66
    じて
    0.66
    考
    0.65
     Englishmen
    0.65
    Activations Density 0.048%

    No Known Activations