© 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. 91066
    Prev
    Next
    INDEX
    Explanations

    free or no cost

    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
    ഞ്
    -0.77
    lorious
    -0.73
    zmir
    -0.71
    telijke
    -0.70
    ズミ
    -0.69
    erees
    -0.67
    gefahr
    -0.66
    يميديا
    -0.66
    wirkung
    -0.66
    údio
    -0.65
    POSITIVE LOGITS
     free
    8.13
    free
    6.31
     FREE
    5.63
    免费
    5.34
    FREE
    5.34
     беспла
    5.03
    Free
    4.88
     Free
    4.72
    無料
    4.59
     бесплатно
    4.50
    Activations Density 0.288%

    No Known Activations