© 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. 26525
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

    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
     it
    -1.40
    ates
    -1.07
     похоже
    -1.05
    ).
    -1.00
    叫做
    -0.98
     themselves
    -0.97
    它们
    -0.96
     M
    -0.96
    把它
    -0.93
    它们的
    -0.91
    POSITIVE LOGITS
     almacenar
    1.29
    蟊
    1.11
     použití
    1.09
    дельник
    1.07
    اعده
    1.05
    ぼく
    1.01
     who
    1.00
     după
    1.00
     desactivar
    1.00
    話の
    0.99
    Activations Density 0.075%

    No Known Activations