© 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. 113656
    Prev
    Next
    INDEX
    Explanations

    adding details or alternatives

    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
     and
    -1.93
     this
    -1.92
    x
    -1.66
    _
    -1.66
     or
    -1.66
    </h3>
    -1.65
    habited
    -1.52
     which
    -1.48
     nadat
    -1.48
     acestei
    -1.47
    POSITIVE LOGITS
    </b>
    1.71
     myös
    1.68
    Also
    1.57
     также
    1.54
     también
    1.52
     également
    1.52
    Additionally
    1.52
     They
    1.51
    我没有
    1.50
    días
    1.50
    Activations Density 0.001%

    No Known Activations