© 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. 81565
    Prev
    Next
    INDEX
    Explanations

    career or district

    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
    inchen
    -0.80
    adakan
    -0.75
    личи
    -0.73
    ieke
    -0.73
     ajedrez
    -0.73
    ridged
    -0.72
     唐
    -0.71
     Accesorios
    -0.71
     leuk
    -0.71
    insula
    -0.69
    POSITIVE LOGITS
    cf
    0.74
    rm
    0.71
    Ў
    0.70
    CDF
    0.69
     burg
    0.68
     Tm
    0.68
     prestations
    0.68
    の形
    0.67
    곗
    0.66
     Bele
    0.66
    Activations Density 0.024%

    No Known Activations