© 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. 22-GEMMASCOPE-RES-131K
    7. 72132
    Prev
    Next
    INDEX
    Explanations

    one that

    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_22/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
     hebat
    -0.95
    Ḧ
    -0.86
    
    -0.85
    înes
    -0.84
     florales
    -0.84
     sobie
    -0.84
    chl
    -0.83
    idać
    -0.82
     ?????
    -0.81
    thats
    -0.81
    POSITIVE LOGITS
     it
    1.70
     worth
    1.18
     not
    1.17
     if
    1.12
     we
    1.11
     one
    1.10
     made
    1.01
     completely
    0.99
     оно
    0.95
     undertaken
    0.94
    Activations Density 0.060%

    No Known Activations