© 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. 102594
    Prev
    Next
    INDEX
    Explanations

    kind of

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

    This neuron activates on phrases of the form “kind of” or “type of” (e.g. “this kind of,” “that type of,” “these kind of”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     mengucap
    -2.00
    
    -1.92
     applau
    -1.88
     uyt
    -1.80
     menyen
    -1.78
    “
    -1.73
    =“
    -1.73
     vann
    -1.72
    hhhhh
    -1.71
     花纹
    -1.70
    POSITIVE LOGITS
     will
    3.11
     would
    2.86
     should
    2.31
     could
    2.25
     might
    1.94
     may
    1.88
     make
    1.77
    Your
    1.77
     must
    1.73
     can
    1.72
    Activations Density 0.029%

    No Known Activations