© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58550
    Prev
    Next
    INDEX
    Explanations

    anticonvulsant or consul

    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
     greateſt
    -2.16
     we
    -2.03
    ឪ
    -2.02
    ſelf
    -2.00
     некоторые
    -1.97
    訁
    -1.95
    actéristi
    -1.89
     два
    -1.88
     They
    -1.88
     باشد
    -1.87
    POSITIVE LOGITS
    \
    2.92
    E
    2.39
    涐
    2.30
    It
    2.22
    ୈ
    2.02
    A
    1.98
    虽
    1.89
    葙
    1.86
    我现在
    1.86
    .“
    1.80
    Activations Density 0.002%

    No Known Activations