© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26087
    Prev
    Next
    INDEX
    Explanations

    colors and materials

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

    The main thing this neuron does is find color words (names of colors).

    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
    TestingModule
    -1.20
    になりますが
    -1.18
    を選択します
    -1.16
    -
    -1.16
    になれる
    -1.13
    づらい
    -1.12
    úst
    -1.09
    をご覧ください
    -1.09
    をお願い
    -1.08
    の概要
    -1.06
    POSITIVE LOGITS
    そして
    1.46
     herbst
    1.37
     作り方
    1.05
     tages
    1.05
    しかし
    1.04
    
    1.03
     그리고
    1.01
     combo
    1.01
    形成
    0.99
     borsa
    0.98
    Activations Density 0.017%

    No Known Activations