© 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. 118966
    Prev
    Next
    INDEX
    Explanations

    the following

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

    The neuron is primarily triggered by numeric tokens (e.g. counts, multi‐digit numbers) in the text.

    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
     senare
    -0.99
    着她
    -0.94
    Sedangkan
    -0.93
    着他
    -0.91
    isuus
    -0.90
    čnost
    -0.89
    火影
    -0.89
    ksessa
    -0.88
    خاذ
    -0.87
    ğlık
    -0.86
    POSITIVE LOGITS
     following
    9.81
    following
    6.72
    Following
    6.00
     siguientes
    5.75
     seguenti
    5.31
     FOLLOWING
    5.19
     folgenden
    5.09
     Following
    5.09
     seguintes
    4.97
     siguiente
    4.81
    Activations Density 0.493%

    No Known Activations