© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84731
    Prev
    Next
    INDEX
    Explanations

    Freddie Gray Ferguson Tray Brown

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

    The neuron is essentially keyed to numeric and date‐related tokens (digits and date/time strings).

    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
    抡
    -0.83
     displaced
    -0.82
     GND
    -0.81
    ppich
    -0.81
    Dina
    -0.81
     الصد
    -0.81
    illoma
    -0.80
    Missions
    -0.80
    排行
    -0.79
    nutie
    -0.79
    POSITIVE LOGITS
     Ferguson
    2.03
    Ferguson
    1.80
    guson
    1.34
     unarmed
    1.25
     Tray
    1.23
     police
    1.16
    Tray
    1.13
     officer
    1.11
     Brown
    1.04
    Brown
    1.04
    Activations Density 0.028%

    No Known Activations