© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27232
    Prev
    Next
    INDEX
    Explanations

    concepts and states

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

    This neuron fires on technical or domain-specific jargon terms (e.g. specialized scientific, medical, statistical, or programming nouns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -1.02
     would
    -0.98
     m
    -0.94
    dinga
    -0.93
     bezeichnen
    -0.93
     to
    -0.92
     x
    -0.91
    视着
    -0.91
     U
    -0.90
    有多少
    -0.90
    POSITIVE LOGITS
     både
    1.02
     sekä
    1.01
     aguja
    1.00
    ᐳ
    1.00
     دیگر
    0.96
     kabát
    0.96
     manguera
    0.96
     cek
    0.96
     dámské
    0.94
     Krzyż
    0.94
    Activations Density 0.160%

    No Known Activations