© 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. 57362
    Prev
    Next
    INDEX
    Explanations

    license type offender

    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
     so
    -0.74
    ناسب
    -0.70
     progressed
    -0.70
    Miri
    -0.70
    ضافة
    -0.69
     pushes
    -0.68
     cole
    -0.66
     booked
    -0.65
    bilden
    -0.65
    保湿
    -0.64
    POSITIVE LOGITS
    naturally
    0.77
    Stuff
    0.75
    orianCalendar
    0.71
    beros
    0.70
     дека
    0.69
     WAIT
    0.69
     entrance
    0.68
    rode
    0.68
    Портал
    0.67
    BRA
    0.67
    Activations Density 0.056%

    No Known Activations