© 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. 22490
    Prev
    Next
    INDEX
    Explanations

    words starting with ben

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

    The neuron activates on the “ben” letter sequence at the start of words (e.g. in drug or compound names).

    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
    e
    -3.17
     хорошая
    -2.38
     of
    -2.36
     a
    -2.36
    鼴
    -2.34
    z
    -2.23
    i
    -2.19
     überprü
    -2.17
     modernen
    -2.14
     erwäh
    -2.13
    POSITIVE LOGITS
    That
    3.05
    What
    2.86
    ଃ
    2.70
    Did
    2.66
    埽
    2.56
    荩
    2.53
    Getting
    2.47
    殽
    2.47
    ༵
    2.44
    Why
    2.41
    Activations Density 0.005%

    No Known Activations