© 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. 10-GEMMASCOPE-RES-131K
    7. 39333
    Prev
    Next
    INDEX
    Explanations

    pole

    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_10/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
    In
    -2.97
     is
    -2.80
    ?
    -2.56
     в
    -2.47
     intrinsically
    -2.34
    噌
    -2.33
    .
    -2.30
    ”
    -2.30
     fearful
    -2.30
     they
    -2.30
    POSITIVE LOGITS
    孥
    3.72
     rajut
    3.06
    汌
    3.03
     aktivi
    3.00
    🫓
    2.95
    ଝ
    2.94
    』(
    2.89
    沄
    2.86
    龶
    2.86
     menyen
    2.83
    Activations Density 0.003%

    No Known Activations