© 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. 119077
    Prev
    Next
    INDEX
    Explanations

    Web of Science

    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
     AIC
    -0.77
     indispens
    -0.77
     통
    -0.75
     dente
    -0.74
     стимули
    -0.73
     гре
    -0.73
     histological
    -0.73
     Parameters
    -0.72
     fout
    -0.71
    Nieder
    -0.71
    POSITIVE LOGITS
    脐
    0.81
    寅
    0.81
    ISI
    0.78
    RCC
    0.76
     vết
    0.73
    兄
    0.73
    abond
    0.73
     Zon
    0.71
    父亲
    0.70
     fugitive
    0.70
    Activations Density 0.086%

    No Known Activations