© 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. 66162
    Prev
    Next
    INDEX
    Explanations

    code keywords and separators

    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
    Aç
    -1.42
    Londres
    -1.27
     cál
    -1.25
    Wrath
    -1.24
    decap
    -1.22
    Diva
    -1.21
    Ꮚ
    -1.21
    yamaha
    -1.21
     célè
    -1.20
    Πηγή
    -1.20
    POSITIVE LOGITS
    L
    1.73
    U
    1.63
    _
    1.62
    f
    1.59
    l
    1.58
    r
    1.57
    y
    1.55
    m
    1.53
    N
    1.52
    Y
    1.52
    Activations Density 0.035%

    No Known Activations