© 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. 112410
    Prev
    Next
    INDEX
    Explanations

    the other way

    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
    {
    -1.84
    0
    -1.70
     jeweiligen
    -1.55
     that
    -1.55
    1
    -1.51
     Bedarf
    -1.48
     other
    -1.45
    ใหญ
    -1.45
    能夠
    -1.45
    ではまた
    -1.44
    POSITIVE LOGITS
     unsere
    1.77
    ción
    1.74
    rceil
    1.62
    熥
    1.57
     unſ
    1.54
     idyl
    1.53
    嗵
    1.52
    umbered
    1.51
    ław
    1.47
     laquelle
    1.47
    Activations Density 0.010%

    No Known Activations