© 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. 93490
    Prev
    Next
    INDEX
    Explanations

    slice and slicing operations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects occurrences of the word “slice” (in any context or casing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     enlightening
    -1.09
    糹
    -1.04
     umož
    -1.03
    ctuaries
    -0.99
    znego
    -0.98
     Unfortunately
    -0.97
    relation
    -0.96
    ᗜ
    -0.95
     masterpiece
    -0.94
    诂
    -0.94
    POSITIVE LOGITS
     slice
    1.82
     Slice
    1.49
    Slice
    1.47
     slicing
    1.46
     slices
    1.46
    slice
    1.28
     sliced
    1.28
     quando
    1.20
    sliced
    1.13
     战
    1.02
    Activations Density 0.009%

    No Known Activations