© 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. 112937
    Prev
    Next
    INDEX
    Explanations

    to (followed by various words)

    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
     resuming
    -1.74
     zeitung
    -1.73
     erzählen
    -1.70
     hilfiger
    -1.65
     lagerfeld
    -1.61
    玉ねぎ
    -1.60
     wohnung
    -1.59
     einfacher
    -1.59
     geburtstag
    -1.59
    quelize
    -1.58
    POSITIVE LOGITS
    糴
    1.88
     Governo
    1.80
    ätigung
    1.65
    呖
    1.57
     brez
    1.55
    "}";
    1.51
     susten
    1.51
     you
    1.51
    饜
    1.51
     alerg
    1.50
    Activations Density 0.035%

    No Known Activations