© 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. 2460
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

    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
    หลัง
    -0.95
    สอบ
    -0.94
    кола
    -0.94
     pData
    -0.92
    公斤
    -0.90
    涐
    -0.90
    neiden
    -0.85
    čne
    -0.85
    成都
    -0.84
     MARKETING
    -0.82
    POSITIVE LOGITS
    閉じ
    0.80
     Bảo
    0.80
    めちゃ
    0.75
    处的
    0.75
    ByUserId
    0.74
     explanatory
    0.73
    now
    0.73
     г
    0.71
    og
    0.71
    people
    0.70
    Activations Density 0.180%

    No Known Activations