© 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. 77169
    Prev
    Next
    INDEX
    Explanations

    patent dates

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

    The neuron detects date-related tokens (e.g. “published,” “issued,” month names, and years) in patent‐reference contexts.

    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
    visel
    -0.79
     цене
    -0.76
     judging
    -0.76
     своє
    -0.75
     Mel
    -0.75
    Faults
    -0.73
     indicador
    -0.73
    IFont
    -0.73
     judgement
    -0.73
     judges
    -0.73
    POSITIVE LOGITS
    June
    0.94
    />
    0.93
    Need
    0.87
    ([]
    0.85
    July
    0.84
     Bapak
    0.84
    Shopping
    0.84
    μμα
    0.84
    OuterAlt
    0.83
    ELTS
    0.82
    Activations Density 0.024%

    No Known Activations