© 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. 33775
    Prev
    Next
    INDEX
    Explanations

    Veterans program exists

    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
     now
    -1.09
     currently
    -1.07
     will
    -1.06
     how
    -1.04
     already
    -1.02
     until
    -0.98
     अब
    -0.94
     口
    -0.93
     must
    -0.93
    巴巴
    -0.92
    POSITIVE LOGITS
    agosto
    1.16
    asantry
    1.13
     نحن
    1.03
     affez
    1.02
     spontan
    1.00
     lavora
    0.99
    νονται
    0.99
    ův
    0.98
     spät
    0.98
    ığımız
    0.97
    Activations Density 0.001%

    No Known Activations