© 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. 56111
    Prev
    Next
    INDEX
    Explanations

    is governed by

    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
    řad
    -0.82
     Bios
    -0.82
     Ransom
    -0.81
    𝖗
    -0.81
     Regex
    -0.79
     lucifer
    -0.79
    RESUMO
    -0.77
    ସ
    -0.77
    Toaster
    -0.77
     Woolf
    -0.75
    POSITIVE LOGITS
     الأشخاص
    0.76
    Expecting
    0.74
    стная
    0.70
    juma
    0.70
     fortalec
    0.69
     chodzi
    0.69
    帷
    0.69
    Dimensiones
    0.68
    たとえば
    0.68
     caminhão
    0.68
    Activations Density 0.237%

    No Known Activations