© 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. 104560
    Prev
    Next
    INDEX
    Explanations

    set alarms

    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
     \
    -1.25
     by
    -1.23
     through
    -1.21
     Please
    -1.12
     For
    -1.10
     Very
    -1.09
     for
    -1.09
     If
    -1.05
     including
    -1.05
     an
    -1.04
    POSITIVE LOGITS
     gigantic
    1.22
    
    1.20
    癭
    1.16
     durabilidad
    1.15
     descuentos
    1.13
     meilleures
    1.12
     composés
    1.11
     modificación
    1.10
     láp
    1.09
     חיצוני
    1.09
    Activations Density 0.000%

    No Known Activations