© 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. 22-GEMMASCOPE-RES-131K
    7. 34635
    Prev
    Next
    INDEX
    Explanations

    "All rights" or "Q:"

    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_22/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
     its
    -1.52
    itaji
    -1.16
     tributo
    -1.04
    жим
    -1.03
    siasi
    -1.03
    剌
    -1.02
    祖国
    -1.02
    ୧
    -1.01
    ！）
    -1.00
     artikkelen
    -1.00
    POSITIVE LOGITS
    er
    1.02
    かれています
    1.02
    udes
    1.02
     aband
    0.98
    kinda
    0.96
    bb
    0.95
    le
    0.95
    Psychiat
    0.94
    napp
    0.93
    indo
    0.92
    Activations Density 0.000%

    No Known Activations