© 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. 62533
    Prev
    Next
    INDEX
    Explanations

    color values and specifications

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

    This neuron activates on numeric tokens and sequences of digits (i.e., it detects numbers).

    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
     what
    -1.26
     purely
    -1.13
     or
    -1.12
     only
    -1.08
     just
    -1.06
     truly
    -1.04
     Without
    -1.03
     without
    -1.03
     that
    -0.99
     one
    -0.95
    POSITIVE LOGITS
     många
    1.11
    0
    1.08
     maniac
    0.99
    рецепт
    0.91
    always
    0.91
    炱
    0.91
    SWEET
    0.89
    MANY
    0.88
    ALWAYS
    0.88
    Mirage
    0.88
    Activations Density 0.119%

    No Known Activations