© 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. 34-GEMMASCOPE-RES-131K
    7. 31103
    Prev
    Next
    INDEX
    Explanations

    worn or custom clinic

    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_34/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
     soportar
    -1.49
     actualizada
    -1.45
     correto
    -1.43
     pulseira
    -1.43
    是因為
    -1.43
     nivelul
    -1.41
     BECAUSE
    -1.40
     equipada
    -1.40
     asegurarse
    -1.38
     ajutor
    -1.37
    POSITIVE LOGITS
     if
    4.06
     to
    3.50
     for
    3.17
     or
    2.89
     yourself
    1.78
     если
    1.77
     instead
    1.76
     as
    1.73
     like
    1.73
     by
    1.73
    Activations Density 0.114%

    No Known Activations