© 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. 10-GEMMASCOPE-RES-131K
    7. 20375
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

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

    The neuron fires strongly on programming identifiers—especially component, tag, or function names (often in PascalCase or camelCase).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    \
    -1.89
     it
    -1.85
     you
    -1.66
    <i>
    -1.59
    *
    -1.48
     people
    -1.41
    },
    -1.41
    >
    -1.37
     A
    -1.30
    }
    -1.28
    POSITIVE LOGITS
    떳
    1.73
     Atención
    1.51
    ープン
    1.48
     Estoy
    1.45
    ícios
    1.45
    Limpiar
    1.43
    Kubernetes
    1.42
     savons
    1.41
    嗐
    1.41
    hidup
    1.39
    Activations Density 0.020%

    No Known Activations