© 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. 66245
    Prev
    Next
    INDEX
    Explanations

    Boat Cards

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

    The neuron is sensitive to numeric literals (e.g. digit sequences, especially hexadecimal numbers) in code.

    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
    "
    -1.13
    }
    -1.04
     Great
    -0.93
     através
    -0.93
    \
    -0.91
     вечера
    -0.90
    1
    -0.90
     masz
    -0.90
     скры
    -0.89
     brinda
    -0.89
    POSITIVE LOGITS
    Etimo
    1.04
    uaikan
    1.03
    Ilustra
    1.02
    onedDateTime
    0.99
    בס
    0.99
    הס
    0.99
    hnung
    0.96
    덥
    0.96
     serupa
    0.96
    Evet
    0.95
    Activations Density 0.000%

    No Known Activations