© 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. 7910
    Prev
    Next
    INDEX
    Explanations

    escaped characters and paths

    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
    櫪
    -2.34
     has
    -2.09
     even
    -2.02
     The
    -1.95
    出来ました
    -1.95
     began
    -1.89
     continued
    -1.83
     which
    -1.80
     since
    -1.77
     used
    -1.77
    POSITIVE LOGITS
    ,&
    2.30
    蓥
    2.27
    
    2.25
     действий
    2.14
     catapult
    2.11
     Partly
    2.09
    其妙
    2.03
    ℓ
    2.03
    
    2.00
    “.
    1.97
    Activations Density 0.006%

    No Known Activations