© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    next-generation [noun]

    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
    hermosa
    -2.20
    
    -2.16
    雱
    -2.14
     ſuch
    -2.11
    ⢅
    -2.08
    尽量
    -2.08
     theſe
    -2.06
    ᨘ
    -2.00
    tamaris
    -1.95
     reizen
    -1.95
    POSITIVE LOGITS
     of
    2.97
    TacToe
    2.20
     как
    2.06
     &
    2.03
     andere
    1.99
    ’
    1.99
    全然
    1.98
     они
    1.91
    You
    1.90
    l
    1.86
    Activations Density 0.008%

    No Known Activations