© 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. 10-GEMMASCOPE-RES-131K
    7. 21534
    Prev
    Next
    INDEX
    Explanations

    Spanish and English mixed text construction

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

    The neuron strongly activates on past‐participle/-ed forms (e.g. “cramped”) used adjectivally.

    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
    }
    -3.27
    手に入
    -2.81
    ☫
    -2.73
    ፨
    -2.70
     renowned
    -2.67
    ]
    -2.64
    眛
    -2.61
    に乗って
    -2.59
     predominantly
    -2.59
    骉
    -2.58
    POSITIVE LOGITS
    There
    3.31
    Some
    3.16
    Many
    2.95
    Perhaps
    2.92
    Every
    2.92
    Quite
    2.91
    Those
    2.86
    Several
    2.84
    One
    2.81
    During
    2.81
    Activations Density 0.002%

    No Known Activations