© 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. 10-GEMMASCOPE-RES-131K
    7. 128649
    Prev
    Next
    INDEX
    Explanations

    Sou followed by various word endings

    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_10/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
    內的
    -2.67
    of
    -2.59
    䜣
    -2.58
     sosteniendo
    -2.55
     intentando
    -2.52
     perdiendo
    -2.48
     její
    -2.36
     amerikanischen
    -2.36
     tratando
    -2.34
     wichtiger
    -2.34
    POSITIVE LOGITS
     proactively
    2.92
     comprehensively
    2.73
     appelez
    2.59
     become
    2.42
    ции
    2.41
    艫
    2.38
    ffichage
    2.38
     cautiously
    2.36
    ного
    2.34
     Lettre
    2.33
    Activations Density 0.002%

    No Known Activations