© 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. 56765
    Prev
    Next
    INDEX
    Explanations

    software license files

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

    The neuron predominantly activates on numeric tokens (digits, version numbers, license 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
     активи
    -0.69
    FK
    -0.69
    hdys
    -0.65
     Etapa
    -0.65
     baffled
    -0.65
     Timur
    -0.65
    чка
    -0.65
     Ladd
    -0.65
     cues
    -0.64
     OnTriggerEnter
    -0.64
    POSITIVE LOGITS
    顶级
    0.72
    querque
    0.71
     kutoka
    0.70
     sauve
    0.68
    StateChange
    0.68
     scha
    0.66
     moze
    0.66
     saturation
    0.66
    ░░
    0.65
    Commonwealth
    0.65
    Activations Density 0.058%

    No Known Activations