© 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. 128084
    Prev
    Next
    INDEX
    Explanations

    dataclass, msc, GenerationType

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

    The neuron flags programming‐language identifier tokens (e.g. class‐, function‐, macro‐, or filename fragments) in code.

    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
    ization
    -2.48
     diriger
    -2.03
     две
    -2.02
    檮
    -1.98
    ciutto
    -1.96
    祤
    -1.94
    鼉
    -1.92
     obud
    -1.92
    的时候
    -1.91
     trouvait
    -1.91
    POSITIVE LOGITS
    (
    2.41
    ین
    2.22
     occasione
    2.20
     that
    2.20
    .’
    2.11
    м
    2.09
     vítima
    2.06
    蝣
    2.05
     spanning
    2.03
    倘
    2.03
    Activations Density 0.001%

    No Known Activations