© 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. 72447
    Prev
    Next
    INDEX
    Explanations

    assuming, version, format, dependencies, ports, importance, updated, Rs

    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
    Lá
    -0.82
    日産
    -0.82
     keny
    -0.79
    dataflow
    -0.78
    ramid
    -0.78
    torio
    -0.78
     Adven
    -0.77
    álogos
    -0.75
     entré
    -0.75
    bilirsiniz
    -0.74
    POSITIVE LOGITS
     None
    0.88
     none
    0.81
    lbs
    0.74
     Новый
    0.73
     associés
    0.73
     hingegen
    0.73
     algumas
    0.72
    幌
    0.71
     والم
    0.71
    None
    0.71
    Activations Density 0.058%

    No Known Activations