© 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. 22-GEMMASCOPE-RES-131K
    7. 68126
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     tuto
    -0.97
    GRAFIA
    -0.94
     manuscrit
    -0.93
    Ν
    -0.91
     Brasília
    -0.89
    儛
    -0.89
     constantes
    -0.88
     kenapa
    -0.86
    loga
    -0.86
     данной
    -0.83
    POSITIVE LOGITS
     did
    1.46
     any
    1.35
    了嗎
    1.16
     теперь
    1.13
    了吗
    1.13
     Did
    1.11
     what
    1.09
     now
    1.06
     anything
    1.04
    任何
    1.04
    Activations Density 0.015%

    No Known Activations