© 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. 34-GEMMASCOPE-RES-131K
    7. 78242
    Prev
    Next
    INDEX
    Explanations

    limitations under the license

    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
    找到了
    -0.91
    orations
    -0.82
     maravill
    -0.82
    ܲ
    -0.73
    máquina
    -0.73
    وزن
    -0.72
    AfterClass
    -0.71
    licaciones
    -0.71
    idental
    -0.69
     Zink
    -0.69
    POSITIVE LOGITS
    гаре
    0.69
     celestial
    0.65
    ය
    0.65
     Joyce
    0.65
    zellen
    0.65
    cookieParser
    0.64
     VOR
    0.63
     freuen
    0.63
     moratorium
    0.63
    ether
    0.62
    Activations Density 0.096%

    No Known Activations