© 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. 10-GEMMASCOPE-RES-131K
    7. 43793
    Prev
    Next
    INDEX
    Explanations

    You know

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

    The neuron specializes in spotting conversational filler or discourse markers—especially colloquial first‐ and second‐person phrases like “you know,” “I mean,” “what I’m saying,” etc.

    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
     your
    -1.48
     a
    -1.29
     وَ
    -1.28
    resas
    -1.28
     cráneo
    -1.21
    
    -1.17
    rawtypes
    -1.17
     where
    -1.16
    orar
    -1.13
    kyr
    -1.12
    POSITIVE LOGITS
    eafter
    1.28
    ING
    1.28
    int
    1.24
    ley
    1.23
     varandra
    1.20
    ৄ
    1.20
    styleUrls
    1.19
    self
    1.16
    laient
    1.16
     hwnd
    1.15
    Activations Density 0.020%

    No Known Activations