© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62595
    Prev
    Next
    INDEX
    Explanations

    hit and variations

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

    this neuron activates on occurrences of the verb “hit” in its various forms (hit, hits, hitting).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    atly
    -0.98
     SHIPPING
    -0.96
    uccess
    -0.95
     hek
    -0.90
    these
    -0.89
    anyo
    -0.88
    u
    -0.87
    cape
    -0.86
     Madeline
    -0.85
    they
    -0.84
    POSITIVE LOGITS
    ched
    1.46
     jackpot
    1.35
     hardest
    1.23
     puberty
    1.13
     podría
    1.07
     the
    1.07
     spots
    1.05
     antwoord
    1.05
     trif
    1.05
     bumps
    0.99
    Activations Density 0.012%

    No Known Activations