© 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. 8301
    Prev
    Next
    INDEX
    Explanations

    drain or weaken

    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
     Currently
    -1.45
     Already
    -1.43
    هما
    -1.38
     Israël
    -1.34
     medier
    -1.27
     marmor
    -1.26
    頭髮
    -1.26
    𝟴
    -1.25
     gese
    -1.23
    𝟲
    -1.23
    POSITIVE LOGITS
    生存
    1.30
     from
    1.25
     by
    1.23
     "
    1.20
    }{
    1.19
     asegur
    1.17
    =
    1.16
     durante
    1.15
     tandis
    1.15
    комнат
    1.12
    Activations Density 0.054%

    No Known Activations