© 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. 21328
    Prev
    Next
    INDEX
    Explanations

    per annum

    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
    ﱠ
    -3.19
     parachoque
    -3.16
    楽しみに
    -2.63
    
    -2.53
    ᭝
    -2.52
    
    -2.52
    ︕
    -2.52
    葙
    -2.42
    どのような
    -2.41
    但却
    -2.38
    POSITIVE LOGITS
    h
    3.50
    o
    3.08
    (
    3.06
    l
    2.81
    —
    2.64
    ma
    2.52
    en
    2.48
     annum
    2.44
    t
    2.44
    le
    2.42
    Activations Density 0.001%

    No Known Activations