© 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. 22-GEMMASCOPE-RES-131K
    7. 25904
    Prev
    Next
    INDEX
    Explanations

    string manipulation and file operations

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

    The neuron is detecting programming code, especially function or method calls signaled by identifier tokens immediately followed by parentheses.

    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
    <h3>
    -1.00
     even
    -0.99
     prevé
    -0.89
    eabouts
    -0.89
     أمريكي
    -0.87
     include
    -0.87
     your
    -0.86
    webtoken
    -0.86
    },
    -0.86
     including
    -0.86
    POSITIVE LOGITS
    ATUM
    1.18
     grosses
    1.12
     lamentable
    1.02
    olni
    1.02
     rechange
    0.99
     enthousi
    0.97
    Deserialize
    0.96
     regata
    0.96
    ATAR
    0.95
     uniforme
    0.94
    Activations Density 0.010%

    No Known Activations