© 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. 59738
    Prev
    Next
    INDEX
    Explanations

    Cory followed by names

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

    The neuron fires on code identifiers used as object or JSON field names (e.g. “fname” and “currentState”).

    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
    }
    -3.77
    ]
    -2.72
     is
    -2.61
    \
    -2.45
     =
    -2.39
    ")
    -2.36
    i
    -2.31
    and
    -2.28
    ","
    -2.23
    </td>
    -2.22
    POSITIVE LOGITS
    嫑
    2.38
    ਗ਼
    2.36
    痾
    2.33
    
    2.31
    苤
    2.30
     ofere
    2.28
    
    2.22
    が届
    2.22
     afectado
    2.20
    饪
    2.20
    Activations Density 0.003%

    No Known Activations