© 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. 39719
    Prev
    Next
    INDEX
    Explanations

    Carlos Pinto, Airline Food, P230

    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
     digno
    -1.46
     discí
    -1.45
     parroquia
    -1.44
     estatua
    -1.37
     sectores
    -1.37
     promociones
    -1.34
     barata
    -1.34
     profesores
    -1.34
     sesiones
    -1.33
     dueños
    -1.32
    POSITIVE LOGITS
     erwähnten
    1.38
     scelte
    1.23
    3
    1.17
     using
    1.16
     Betracht
    1.13
    6
    1.12
    7
    1.10
     Empty
    1.09
    Because
    1.09
    2
    1.08
    Activations Density 0.007%

    No Known Activations