© 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. 10-GEMMASCOPE-RES-131K
    7. 44865
    Prev
    Next
    INDEX
    Explanations

    well behaved

    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_10/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
     
    -1.92
     –
    -1.84
    了一会儿
    -1.66
    ↵↵
    -1.50
     “
    -1.43
    一趟
    -1.39
    着自己的
    -1.35
     is
    -1.34
     have
    -1.30
    一阵
    -1.23
    POSITIVE LOGITS
    遄
    1.52
    inerario
    1.51
    '])){
    1.48
    }],
    1.45
    にします
    1.38
     nasze
    1.34
    umesc
    1.34
     "]";
    1.33
    tså
    1.32
     orologio
    1.32
    Activations Density 0.079%

    No Known Activations