© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13325
    Prev
    Next
    INDEX
    Explanations

    operations performed many times

    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
     ваз
    -1.38
     cordón
    -1.27
     Rät
    -1.13
     lecker
    -1.12
    heses
    -1.09
     прокура
    -1.09
     controversy
    -1.09
    textTheme
    -1.07
     rompecabezas
    -1.05
     Trauer
    -1.05
    POSITIVE LOGITS
     each
    1.55
    specially
    1.10
    亟
    1.09
     barbacoa
    1.06
     luxo
    1.06
     interfacial
    1.04
     required
    1.04
     broderie
    1.02
     every
    0.99
    pæ
    0.99
    Activations Density 0.086%

    No Known Activations