© 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. 33731
    Prev
    Next
    INDEX
    Explanations

    buttons for hiding or deleting

    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
    Then
    -0.98
    There
    -0.95
    ambassade
    -0.94
     optimieren
    -0.93
     that
    -0.93
    ötä
    -0.90
    âge
    -0.89
    Since
    -0.88
     razões
    -0.88
    Because
    -0.88
    POSITIVE LOGITS
    fraud
    0.96
    喇叭
    0.89
    🗿
    0.88
     fraud
    0.88
     LOAN
    0.87
     CONGRESS
    0.86
     logement
    0.85
    Enquiries
    0.85
     nah
    0.84
     werd
    0.84
    Activations Density 0.024%

    No Known Activations