© 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. 34-GEMMASCOPE-RES-131K
    7. 63471
    Prev
    Next
    INDEX
    Explanations

    comment and code delimiters

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

    This neuron appears to be inactive (it never fires) and thus does not detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -1.28
     wyra
    -1.23
     wypo
    -1.13
    psfrag
    -1.06
     tłuma
    -1.05
     músico
    -1.04
     uczest
    -1.02
     verá
    -1.02
     claramente
    -1.01
    neiden
    -1.01
    POSITIVE LOGITS
    if
    1.56
     if
    1.36
    1.29
     here
    1.18
    for
    1.16
    这
    1.16
     ,'
    1.13
     perchè
    1.09
    tifiable
    1.09
    pography
    1.09
    Activations Density 0.011%

    No Known Activations