© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77218
    Prev
    Next
    INDEX
    Explanations

    axial slice orientation

    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
    рыя
    -0.79
    PerSecond
    -0.78
     muualla
    -0.78
    booking
    -0.76
     oxides
    -0.76
    lihood
    -0.75
    endpush
    -0.75
     ngunit
    -0.74
    >$
    -0.73
    nejšie
    -0.73
    POSITIVE LOGITS
     slices
    1.57
     slice
    1.53
     coronal
    1.49
    slices
    1.37
     axial
    1.30
    slice
    1.25
     sagit
    1.24
    Slice
    1.21
     Slice
    1.17
     transversal
    1.16
    Activations Density 0.140%

    No Known Activations