© 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. 13646
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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
     by
    -1.20
     at
    -0.96
     тобой
    -0.91
     while
    -0.90
     CGRect
    -0.89
    殲
    -0.89
     dziennik
    -0.89
     pengalaman
    -0.89
     and
    -0.88
     on
    -0.87
    POSITIVE LOGITS
     kado
    1.12
     Yani
    1.05
    ölkerung
    1.05
    ఉ
    1.04
     ";
    1.04
     इसलिए
    1.01
     paradis
    1.01
     élas
    1.00
     palio
    0.99
     Jornada
    0.98
    Activations Density 0.032%

    No Known Activations