© 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. 71375
    Prev
    Next
    INDEX
    Explanations

    common interest

    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
     unſ
    -1.79
     ſeveral
    -1.60
     Perſ
    -1.51
     ſever
    -1.49
     faſt
    -1.45
     ſta
    -1.45
     Diſ
    -1.43
     leſs
    -1.43
     Inſ
    -1.42
     favoris
    -1.39
    POSITIVE LOGITS
    For
    1.45
    G
    1.32
    K
    1.29
    However
    1.28
    This
    1.27
    With
    1.26
    這些
    1.26
     While
    1.24
     With
    1.24
    It
    1.24
    Activations Density 0.819%

    No Known Activations