© 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. 84221
    Prev
    Next
    INDEX
    Explanations

    programming generator iterables

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

    The neuron fires strongly on the asterisk “*” token used in code (especially generator‐function syntax).

    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
     What
    -1.84
    what
    -1.57
    cellona
    -1.56
     feeble
    -1.56
     you
    -1.49
     seminal
    -1.48
    氛围
    -1.47
    诅
    -1.47
     religiosas
    -1.46
    花板
    -1.43
    POSITIVE LOGITS
     of
    2.11
    </sup>
    1.64
     etc
    1.56
     also
    1.56
    </h4>
    1.47
    ientras
    1.45
    ].
    1.43
    ])
    1.38
    ])
    1.38
    visionnement
    1.36
    Activations Density 0.002%

    No Known Activations