© 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. 10-GEMMASCOPE-RES-131K
    7. 83647
    Prev
    Next
    INDEX
    Explanations

    help and support

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

    The neuron activates on words and phrases expressing that something is done “with help,” “with assistance,” or “with support” from someone or something.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     for
    -2.28
     not
    -2.19
     before
    -1.82
     if
    -1.72
     in
    -1.68
    because
    -1.67
     on
    -1.66
     just
    -1.62
     bukanlah
    -1.49
     when
    -1.45
    POSITIVE LOGITS
    ଃ
    1.73
    阄
    1.70
    跸
    1.61
    larak
    1.60
    谞
    1.58
     ekip
    1.57
     بعض
    1.57
     témo
    1.57
     enorme
    1.56
     Beberapa
    1.56
    Activations Density 0.014%

    No Known Activations