© 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. 38668
    Prev
    Next
    INDEX
    Explanations

    file headers and licenses

    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
     
    -0.70
    ässä
    -0.69
    섰
    -0.68
    yeli
    -0.68
     Suits
    -0.66
    æg
    -0.65
     asistencia
    -0.65
     Stacy
    -0.65
    変わる
    -0.63
     タン
    -0.63
    POSITIVE LOGITS
    EqualsAnd
    0.76
    subj
    0.73
    ލ
    0.73
     axon
    0.72
     легко
    0.70
    ripsi
    0.69
    doctype
    0.69
    Lif
    0.69
     middleware
    0.69
    inkai
    0.68
    Activations Density 0.078%

    No Known Activations