© 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. 110483
    Prev
    Next
    INDEX
    Explanations

    wait for

    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
     \
    -2.42
     zwanzig
    -2.36
     最后
    -2.27
    ではない
    -2.25
    indest
    -2.20
     نکته
    -2.14
     yalnızca
    -2.14
     paździer
    -2.06
     zwölf
    -2.06
     of
    -2.02
    POSITIVE LOGITS
    ers
    2.89
    {
    2.78
     uſed
    2.36
     руке
    2.25
     هایی
    2.08
    寕
    2.06
     casero
    2.05
    硨
    2.03
    嚆
    2.03
    蕷
    2.03
    Activations Density 0.005%

    No Known Activations