© 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. 118388
    Prev
    Next
    INDEX
    Explanations

    licensing or comments

    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
    ҽ
    -0.85
    thylene
    -0.81
    uity
    -0.77
     except
    -0.76
    breed
    -0.76
    plings
    -0.76
     shepherds
    -0.75
    fields
    -0.75
    헤
    -0.75
    ert
    -0.75
    POSITIVE LOGITS
     last
    0.73
     many
    0.72
    Quercus
    0.71
    Ḵ
    0.70
    өз
    0.70
    tols
    0.68
    łys
    0.68
    kover
    0.68
    ₉
    0.67
    멈
    0.66
    Activations Density 0.001%

    No Known Activations