© 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. 38551
    Prev
    Next
    INDEX
    Explanations

    epilepsy

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

    layout-related elements in software code, particularly in Android development.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron never fires on any of the tokens shown, so it isn’t detecting any pattern in these examples.

    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
     to
    -1.32
     because
    -1.11
    >
    -0.97
     extraordinaria
    -0.89
    اطر
    -0.85
     ;"
    -0.84
    ";
    -0.83
    cestry
    -0.82
     TÉCN
    -0.82
     tablespoons
    -0.81
    POSITIVE LOGITS
    @[+][
    1.07
    LOAT
    1.00
     centralized
    1.00
    })()
    1.00
    GENERIC
    0.99
     desay
    0.98
     ellas
    0.98
    ()]);
    0.96
    ünün
    0.95
    Tinh
    0.95
    Activations Density 0.000%

    No Known Activations