© 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. 42197
    Prev
    Next
    INDEX
    Explanations

    digging deeper 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
    梣
    -2.39
    (ﾟ
    -2.31
    目次
    -2.27
     köpa
    -2.25
    følgelig
    -2.23
    (￣
    -2.20
    鈊
    -2.20
    当你
    -2.20
    倂
    -2.19
     時尚
    -2.14
    POSITIVE LOGITS
     into
    2.63
     overarching
    2.52
    in
    2.47
    ."
    2.44
    1
    2.36
     ‘
    2.28
     começaram
    2.16
    ",
    2.05
     ???
    2.03
     
    2.03
    Activations Density 0.002%

    No Known Activations