© 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. 104884
    Prev
    Next
    INDEX
    Explanations

    transition from to into

    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
    )」
    -2.14
     underlines
    -2.05
     Abweich
    -2.02
     wykonane
    -2.02
     adjoining
    -2.02
     accompanying
    -2.00
    sandalia
    -1.93
    鋦
    -1.90
     sogen
    -1.88
     weiteres
    -1.88
    POSITIVE LOGITS
    ”
    2.13
    ?
    2.11
    !
    2.09
    。
    1.95
    welli
    1.95
     как
    1.91
     &
    1.91
    芣
    1.87
    .”
    1.83
    oczes
    1.81
    Activations Density 0.015%

    No Known Activations