© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72219
    Prev
    Next
    INDEX
    Explanations

    by way of

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

    The neuron selectively activates on specialized scientific or technical nouns (especially biological and medical process terms).

    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
    ENDS
    -0.96
    Jackson
    -0.90
     исчез
    -0.89
     نداشت
    -0.88
    ))){
    -0.87
     všet
    -0.85
    Alpha
    -0.85
    farbe
    -0.84
    Apple
    -0.83
    urns
    -0.82
    POSITIVE LOGITS
     through
    1.83
     via
    1.68
     using
    1.53
     by
    1.45
     melalui
    1.32
     with
    1.26
     tramite
    1.24
     courtesy
    1.10
     from
    1.09
     in
    1.05
    Activations Density 0.151%

    No Known Activations