© 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. 26406
    Prev
    Next
    INDEX
    Explanations

    transition from punctuation to new clause

    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
     proteine
    -0.96
     regarder
    -0.94
     contempla
    -0.94
     fono
    -0.93
     curiosa
    -0.92
     posa
    -0.91
     denuncia
    -0.90
     lez
    -0.90
     you
    -0.90
     definitivamente
    -0.90
    POSITIVE LOGITS
     además
    1.15
    뿐
    1.00
     why
    0.97
    況
    0.96
     oppure
    0.96
     but
    0.96
     numerosos
    0.94
     przecież
    0.93
     além
    0.93
     avrebbero
    0.93
    Activations Density 0.026%

    No Known Activations