© 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. 84461
    Prev
    Next
    INDEX
    Explanations

    sharing with the world

    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
     then
    -1.49
     or
    -1.48
     núm
    -1.38
     mía
    -1.33
     fahrrad
    -1.30
     I
    -1.30
    ）。
    -1.25
    ømme
    -1.24
    ми
    -1.23
     tejidos
    -1.22
    POSITIVE LOGITS
    !
    1.70
     !(
    1.48
    荭
    1.46
    جهة
    1.39
    Though
    1.37
    woners
    1.36
    룬
    1.36
    Perhaps
    1.35
    Maybe
    1.34
    Although
    1.33
    Activations Density 0.020%

    No Known Activations