© 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. 227
    Prev
    Next
    INDEX
    Explanations

    historians and history

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

    The neuron fires on mentions of “historian” and related occurrences of “history” (i.e. references to the academic discipline or its practitioners).

    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
     zimowa
    -1.29
     étroite
    -1.01
    喲
    -1.00
    鞏
    -1.00
     apenas
    -1.00
    PYX
    -0.98
    彼らの
    -0.98
     stats
    -0.98
     urod
    -0.98
    的名字
    -0.98
    POSITIVE LOGITS
     museums
    1.48
     museum
    1.23
    Historic
    1.21
     Museums
    1.21
     historians
    1.20
     HISTORICAL
    1.19
     HISTOR
    1.13
     citazioni
    1.13
     Histor
    1.12
     historical
    1.09
    Activations Density 0.105%

    No Known Activations