© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60070
    Prev
    Next
    INDEX
    Explanations

    code snippets in web frameworks

    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_10/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
     antiguas
    -1.44
     extremadamente
    -1.35
     szpital
    -1.27
    brać
    -1.25
     antiguos
    -1.25
     olvidado
    -1.23
     cambiado
    -1.22
     cheia
    -1.21
     escuchado
    -1.20
     comenzado
    -1.16
    POSITIVE LOGITS
     their
    1.64
     until
    1.22
     any
    1.21
     when
    1.16
     than
    1.10
    Compte
    1.09
     Tutte
    1.08
     ۱۴۰۰
    1.07
    surate
    1.07
     їх
    1.07
    Activations Density 0.019%

    No Known Activations