© 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. 63786
    Prev
    Next
    INDEX
    Explanations

    the object surface or part

    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
    orious
    -1.23
    ')}}"
    -1.12
     THOSE
    -1.10
     norvég
    -1.10
     yeni
    -1.10
     réf
    -1.09
     új
    -1.09
     součas
    -1.08
    ofing
    -1.08
    werken
    -1.08
    POSITIVE LOGITS
     entire
    2.16
     outside
    2.06
     already
    1.92
     edges
    1.92
     sides
    1.90
     ends
    1.81
     beginning
    1.79
     same
    1.71
     inside
    1.69
     area
    1.56
    Activations Density 0.130%

    No Known Activations