© 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. 33060
    Prev
    Next
    INDEX
    Explanations

    database, code, configuration

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

    The neuron fires strongly on code identifiers (especially snake_case or other multi-part names with underscores).

    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
     during
    -0.96
     until
    -0.92
    ၉
    -0.90
    charlotte
    -0.85
    islamic
    -0.85
    russian
    -0.85
     kapcs
    -0.84
    michelle
    -0.83
    hollywood
    -0.83
     Usually
    -0.83
    POSITIVE LOGITS
    tose
    0.91
    `{.
    0.89
    ost
    0.87
     gigantic
    0.87
     them
    0.87
    ఝ
    0.86
    叹息
    0.85
     поч
    0.85
    ulha
    0.85
    鹩
    0.84
    Activations Density 0.050%

    No Known Activations