© 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. 45202
    Prev
    Next
    INDEX
    Explanations

    vertical structures or states

    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
     to
    -1.70
    zembro
    -1.68
     for
    -1.51
     ۱۵
    -1.51
     wonderful
    -1.40
    zember
    -1.40
     konkret
    -1.38
     geografia
    -1.38
     และ
    -1.35
     ۲۰۰
    -1.35
    POSITIVE LOGITS
     there
    1.49
    :
    1.49
    /
    1.41
     там
    1.34
    álním
    1.34
     godzin
    1.33
     the
    1.24
    アシ
    1.22
     oreja
    1.22
     comodidad
    1.19
    Activations Density 0.732%

    No Known Activations