© 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. 22-GEMMASCOPE-RES-131K
    7. 27479
    Prev
    Next
    INDEX
    Explanations

    Scene graph contexts

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

    The neuron fires on occurrences of the word “scene” (in any form or context).

    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
    姈
    -2.83
    酲
    -2.63
    婞
    -2.61
    椟
    -2.53
    怎么可能
    -2.45
    媗
    -2.39
    焄
    -2.38
    ⽌
    -2.25
    ⽩
    -2.25
    
    -2.23
    POSITIVE LOGITS
    '
    3.78
    ⑊
    2.84
    (
    2.58
    "
    2.56
    i
    2.45
     rasch
    2.23
     представители
    2.11
    崀
    2.08
     manches
    2.06
    不错的
    2.06
    Activations Density 0.007%

    No Known Activations