© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1069
    Prev
    Next
    INDEX
    Explanations

    consultation, Growth, Ocean, Q, 1, Very

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

    The neuron spotlights sequences of capitalized words and acronyms that form formal place- or project-designation headers (e.g. “Special Protection Area (SPA)”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Reichs
    -0.82
     Empire
    -0.74
     Equations
    -0.73
     diperhatikan
    -0.71
    TCA
    -0.71
    toluene
    -0.68
    ingo
    -0.67
     عمليات
    -0.66
    ūsų
    -0.66
     Application
    -0.65
    POSITIVE LOGITS
     inspector
    0.86
     DPD
    0.85
    uktur
    0.83
     blush
    0.82
     molle
    0.81
     soundness
    0.81
    サウンド
    0.79
    ירים
    0.78
     preparation
    0.77
    êche
    0.77
    Activations Density 0.005%

    No Known Activations