© 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. 93163
    Prev
    Next
    INDEX
    Explanations

    code structure and file paths

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

    The neuron flags technical “code” fragments—strings of programming-style identifiers, symbols, and markup rather than ordinary running text.

    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
    DispatchQueue
    -0.87
    offsetX
    -0.86
     homeowners
    -0.85
     verursacht
    -0.85
    สอง
    -0.83
    Cust
    -0.81
    Action
    -0.81
    GenerationType
    -0.81
     possibilité
    -0.80
     juillet
    -0.79
    POSITIVE LOGITS
    各有
    1.02
    にします
    1.02
    蜥
    0.97
    頚
    0.93
    Lugares
    0.93
     contratto
    0.93
     but
    0.92
    出来て
    0.91
     unterschied
    0.90
    OfSize
    0.90
    Activations Density 0.036%

    No Known Activations