© 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. 35766
    Prev
    Next
    INDEX
    Explanations

    all or some

    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
     (
    -1.37
    ána
    -1.30
    ̣n
    -1.27
     ONLY
    -1.10
    ęs
    -1.08
     Tirol
    -1.08
    nak
    -1.05
     Lübeck
    -1.02
    oncé
    -1.02
    طق
    -1.02
    POSITIVE LOGITS
     anunció
    1.46
     aseguró
    1.31
     übernommen
    1.30
     wiesz
    1.28
     of
    1.26
     Fuerzas
    1.23
     czemu
    1.23
     verkoop
    1.22
    jours
    1.20
     fecond
    1.19
    Activations Density 0.070%

    No Known Activations