© 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. 34-GEMMASCOPE-RES-131K
    7. 108550
    Prev
    Next
    INDEX
    Explanations

    sports, events, places, or organizations

    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
     and
    -1.75
    や
    -1.33
     entire
    -1.20
     и
    -1.11
    ?'
    -1.01
    U
    -0.98
    性和
    -0.96
    I
    -0.94
     gesamten
    -0.94
     it
    -0.93
    POSITIVE LOGITS
     sés
    1.38
     perfecte
    1.35
     marbre
    1.30
     marchand
    1.28
     sementes
    1.25
     enthou
    1.24
     caiu
    1.24
     dreaming
    1.24
    ܖ
    1.23
     tabac
    1.22
    Activations Density 0.170%

    No Known Activations