© 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. 39158
    Prev
    Next
    INDEX
    Explanations

    getParcelableExtra

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

    The neuron is triggered by numeric literals in code (i.e. integers appearing in the source).

    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
    rmk
    -0.99
    coop
    -0.98
     była
    -0.93
     coop
    -0.91
    wast
    -0.85
    vlád
    -0.85
     sorprend
    -0.84
    Designs
    -0.81
     ediciones
    -0.80
     amikor
    -0.80
    POSITIVE LOGITS
     populated
    1.09
    ➖➖
    1.00
     Populate
    0.99
    無限
    0.98
     presently
    0.95
     desinf
    0.91
    ónimo
    0.91
    vač
    0.90
     luminos
    0.90
    Ngo
    0.90
    Activations Density 0.011%

    No Known Activations