© 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. 92896
    Prev
    Next
    INDEX
    Explanations

    lecture number followed by of or coach name

    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
    หรือ
    -1.14
     esponja
    -1.03
     curieux
    -1.01
     câble
    -1.01
     актриса
    -1.00
    代目
    -0.97
     équilibr
    -0.96
     favoris
    -0.95
     bicicletas
    -0.94
    ixe
    -0.94
    POSITIVE LOGITS
     is
    0.99
    bucks
    0.98
    nal
    0.98
    na
    0.94
     further
    0.93
    borns
    0.93
    st
    0.92
    umers
    0.91
    heck
    0.90
    ness
    0.89
    Activations Density 0.002%

    No Known Activations