© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59605
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or common phrases

    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
    czego
    -0.81
     Frankfurt
    -0.80
    ѭ
    -0.78
     東京都
    -0.78
     麗
    -0.78
     frankfurt
    -0.76
    名稱
    -0.75
    午餐
    -0.74
    窦
    -0.74
     aimed
    -0.73
    POSITIVE LOGITS
     Subsid
    0.90
     dredged
    0.79
    стема
    0.77
    Protos
    0.77
     Mateo
    0.76
    푏
    0.75
    昨日は
    0.74
     Hege
    0.73
    haviours
    0.73
    ishments
    0.73
    Activations Density 0.000%

    No Known Activations