© 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. 128129
    Prev
    Next
    INDEX
    Explanations

    nonprofit organizations

    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
    悩む
    -1.73
     metody
    -1.70
    呿
    -1.68
     the
    -1.63
    
    -1.61
     overwhelming
    -1.59
     novin
    -1.59
    鹋
    -1.55
    ありが
    -1.53
     beträ
    -1.52
    POSITIVE LOGITS
    ’
    1.73
    ⢓
    1.49
    tona
    1.49
    issime
    1.35
    »),
    1.35
    cuencia
    1.34
    
    1.32
    ним
    1.30
    erializer
    1.29
    »;
    1.28
    Activations Density 0.012%

    No Known Activations