© 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. 22-GEMMASCOPE-RES-131K
    7. 129206
    Prev
    Next
    INDEX
    Explanations

    past events and future

    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
    OTTEN
    -1.02
     sehr
    -0.98
     ejército
    -0.97
     flechas
    -0.97
     colchón
    -0.94
    områ
    -0.93
    miljø
    -0.92
    weka
    -0.92
     hatta
    -0.90
     acento
    -0.90
    POSITIVE LOGITS
     also
    1.77
     said
    1.69
     further
    1.43
     Tuesday
    1.37
     kuitenkin
    1.32
     però
    1.30
     também
    1.30
     Wednesday
    1.20
     saranno
    1.13
     также
    1.13
    Activations Density 0.155%

    No Known Activations