© 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. 84130
    Prev
    Next
    INDEX
    Explanations

    hidden items

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

    The neuron activates strongly on occurrences of the word “hidden.”

    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
     また
    -2.70
    (
    -2.39
    鲥
    -2.31
    絰
    -2.19
    呖
    -2.09
    k
    -2.08
     crede
    -2.06
    儅
    -2.00
    o
    -1.99
    —
    -1.98
    POSITIVE LOGITS
    ୌ
    2.59
    नलोड
    2.45
    Reparto
    2.30
    lossians
    2.23
     diciendo
    2.23
    葎
    2.20
    
    2.20
    pecabe
    2.20
    不愿意
    2.16
    писок
    2.14
    Activations Density 0.006%

    No Known Activations