© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68165
    Prev
    Next
    INDEX
    Explanations

    `MyStream` or `FiniteStream`

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

    This neuron fires on code tokens—keywords, identifiers, type names, and other programming‐language syntax elements.

    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
    Appellant
    -0.96
    yorsunuz
    -0.94
    hoodie
    -0.93
    },
    -0.90
    </td>
    -0.89
    不会
    -0.88
    图片
    -0.88
     not
    -0.87
    mule
    -0.87
    hawaii
    -0.87
    POSITIVE LOGITS
    եց
    1.02
    Gön
    1.01
    Groet
    1.00
     HAPPENED
    0.99
     WANTED
    0.99
    rimid
    0.99
    payers
    0.98
     उन्ह
    0.97
    看你
    0.96
     BENE
    0.95
    Activations Density 0.005%

    No Known Activations