© 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. 65634
    Prev
    Next
    INDEX
    Explanations

    CSS selectors and tags

    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
     tampoco
    -0.73
    色的
    -0.69
     out
    -0.67
    вяза
    -0.67
    捎
    -0.67
     Forscher
    -0.66
     Iris
    -0.65
     kemudian
    -0.65
     Vs
    -0.65
     Garry
    -0.63
    POSITIVE LOGITS
     ristoranti
    0.73
    toEqual
    0.72
    ขอบคุณ
    0.71
    ℬ
    0.69
    ykite
    0.69
    องค์
    0.68
    ukur
    0.68
     Outlet
    0.68
     Murdock
    0.68
     contacter
    0.67
    Activations Density 0.040%

    No Known Activations