© 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. 16069
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    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
    '';
    -1.16
     would
    -1.13
    &,
    -1.13
    stwo
    -1.10
    ledad
    -1.09
     curio
    -1.05
    istical
    -1.00
    preneur
    -1.00
    :''
    -0.99
    了一种
    -0.99
    POSITIVE LOGITS
     we
    1.30
     our
    1.24
    larımız
    1.13
    octubre
    1.10
    Sometimes
    1.06
    Already
    1.02
     already
    0.97
    Our
    0.97
     damos
    0.96
    気がします
    0.95
    Activations Density 0.078%

    No Known Activations