© 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. 10-GEMMASCOPE-RES-131K
    7. 47962
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     hicimos
    -1.69
     altamente
    -1.41
     its
    -1.39
    ginger
    -1.36
    nitř
    -1.33
     sencillos
    -1.31
    ベトナム
    -1.31
     cercanos
    -1.30
    toddler
    -1.30
    几位
    -1.28
    POSITIVE LOGITS
     They
    1.66
     also
    1.58
     they
    1.54
     of
    1.53
     их
    1.50
    𓆜
    1.50
     themselves
    1.48
    itizing
    1.43
    lare
    1.41
    ்
    1.40
    Activations Density 0.083%

    No Known Activations