© 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. 34-GEMMASCOPE-RES-131K
    7. 60575
    Prev
    Next
    INDEX
    Explanations

    atra / attr words and related suffixes/completions

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

    The neuron responds to tokens containing the character sequence “atr” (e.g. Atraumatic, attraction, ATR, attr).

    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
     метод
    -0.75
     />";
    -0.75
    𝕍
    -0.71
    一首
    -0.71
     Oe
    -0.70
     Bracken
    -0.70
     Temples
    -0.70
    蜴
    -0.68
     dư
    -0.67
    shut
    -0.67
    POSITIVE LOGITS
     attra
    0.99
    attra
    0.88
     attractions
    0.81
     polluted
    0.81
    mView
    0.80
     attr
    0.78
    VOD
    0.74
    igas
    0.73
     attraction
    0.73
    Attra
    0.72
    Activations Density 0.020%

    No Known Activations