© 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. 22-GEMMASCOPE-RES-131K
    7. 65608
    Prev
    Next
    INDEX
    Explanations

    that introducing clauses

    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
    푼
    -1.43
    闈
    -1.39
    icação
    -1.34
     жовтня
    -1.34
    inut
    -1.34
    anız
    -1.33
     accél
    -1.33
    蜚
    -1.30
     pandémie
    -1.30
     canadienne
    -1.30
    POSITIVE LOGITS
     it
    3.19
     they
    2.64
     that
    2.05
     there
    2.02
     we
    1.64
     was
    1.56
    for
    1.42
    '
    1.39
     consequently
    1.38
     you
    1.32
    Activations Density 0.008%

    No Known Activations