© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21171
    Prev
    Next
    INDEX
    Explanations

    how to / link

    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
     by
    -1.80
     one
    -1.66
     when
    -1.65
     its
    -1.48
     was
    -1.45
     this
    -1.45
     as
    -1.34
    🍔
    -1.33
     for
    -1.33
     any
    -1.31
    POSITIVE LOGITS
     alguno
    1.48
     komplet
    1.36
     algún
    1.36
    Recursos
    1.35
     innych
    1.34
    Արտ
    1.32
    ypeł
    1.30
    菝
    1.30
    Beneficios
    1.30
     тільки
    1.30
    Activations Density 0.016%

    No Known Activations