© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66305
    Prev
    Next
    INDEX
    Explanations

    True or YES

    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_22/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
    itions
    -0.98
     then
    -0.93
    ためには
    -0.90
     overzicht
    -0.90
    îtra
    -0.89
    FieldType
    -0.88
    (){}
    -0.87
    lees
    -0.85
     Rücks
    -0.82
    看不到
    -0.81
    POSITIVE LOGITS
    Leading
    1.09
     "")
    1.09
    Commentaires
    1.06
    Yum
    1.04
     sosteniendo
    1.02
    Numerous
    1.02
    Nearly
    1.00
    nosotros
    1.00
    surate
    0.99
    Significado
    0.98
    Activations Density 0.001%

    No Known Activations