© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38380
    Prev
    Next
    INDEX
    Explanations

    code comments or technical terms

    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
    ContextCompat
    -1.14
     volverá
    -1.01
    ъек
    -1.00
     comenzará
    -0.98
    Ծանոթ
    -0.96
    |[]
    -0.95
    ERVIEW
    -0.95
     permitirá
    -0.94
     zari
    -0.94
    cknow
    -0.93
    POSITIVE LOGITS
     also
    1.02
    答え
    0.91
     Hinsicht
    0.88
    answers
    0.84
    他們
    0.82
     terça
    0.81
     Pir
    0.80
    不时
    0.80
    quis
    0.79
     районе
    0.79
    Activations Density 0.001%

    No Known Activations