© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    shell variable expansion

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

    This neuron fires on numeric constants (i.e. tokens made up of digits) within code or scripts.

    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
     where
    -0.89
    償
    -0.85
     acoso
    -0.82
    ccccccc
    -0.80
     many
    -0.78
    đen
    -0.78
     historic
    -0.78
    DCC
    -0.75
     históricas
    -0.75
     while
    -0.75
    POSITIVE LOGITS
    ##
    0.95
     Sculpt
    0.86
    :%
    0.85
     responsabilité
    0.85
    [@
    0.84
    %%
    0.82
     Viitattu
    0.82
     девушек
    0.82
    ylated
    0.81
    /%
    0.81
    Activations Density 0.028%

    No Known Activations