© 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. 44155
    Prev
    Next
    INDEX
    Explanations

    kind of [description]

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

    This neuron detects hedge phrases, especially occurrences of “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
    Ꮉ
    -2.38
    8
    -2.22
    3
    -2.11
    2
    -2.09
    你这个
    -2.08
    <b>
    -2.02
    7
    -2.02
    9
    -2.00
    4
    -1.97
     altes
    -1.95
    POSITIVE LOGITS
    Eucalyptus
    1.78
    出一个
    1.77
    __':
    1.73
     ولی
    1.69
    ுகள்
    1.68
    ällig
    1.68
    亓
    1.66
    泚
    1.64
    でしょ
    1.64
     然
    1.63
    Activations Density 0.006%

    No Known Activations