© 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. 16230
    Prev
    Next
    INDEX
    Explanations

    checkout, cart, and basket actions

    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
    titleMargin
    -0.97
     CallOverrides
    -0.96
     restTemplate
    -0.96
     terrified
    -0.95
    mgren
    -0.94
    fect
    -0.93
     efekty
    -0.91
     here
    -0.91
     in
    -0.89
    برد
    -0.89
    POSITIVE LOGITS
     finalize
    1.34
     final
    1.27
    kę
    1.19
    웹
    1.18
    Final
    1.14
    ötet
    1.07
     wybrać
    1.06
    final
    1.05
     prüfen
    1.05
    ftrag
    1.05
    Activations Density 0.052%

    No Known Activations