© 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. 15244
    Prev
    Next
    INDEX
    Explanations

    URLs and code delimiters

    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
    駸
    -0.91
    tų
    -0.86
     Bookings
    -0.84
     vices
    -0.84
     vaguely
    -0.83
     scarcely
    -0.82
     rhum
    -0.82
     funghi
    -0.82
     شامل
    -0.81
     hardly
    -0.81
    POSITIVE LOGITS
     weten
    1.05
    恥ず
    1.02
     nejlepší
    0.99
     zarówno
    0.98
    Kritik
    0.97
     impresionantes
    0.96
     salvajes
    0.96
     ganadores
    0.95
     dibujos
    0.95
     několik
    0.94
    Activations Density 0.000%

    No Known Activations