© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69241
    Prev
    Next
    INDEX
    Explanations

    classic typical standard

    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
    paces
    -1.37
    atized
    -1.29
    ครื่อง
    -1.29
    thodoxy
    -1.28
    hirts
    -1.28
    pecies
    -1.26
    tilles
    -1.23
    hooting
    -1.21
    lograph
    -1.20
     ín
    -1.20
    POSITIVE LOGITS
     American
    1.66
     European
    1.56
     of
    1.52
     typical
    1.45
     from
    1.44
     California
    1.40
     old
    1.37
     British
    1.36
     típico
    1.28
     like
    1.27
    Activations Density 0.032%

    No Known Activations