© 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. 10-GEMMASCOPE-RES-131K
    7. 100678
    Prev
    Next
    INDEX
    Explanations

    free from negative attributes

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

    The neuron specifically activates on the standalone word “free.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    紆
    -2.05
    多い
    -1.99
    ままで
    -1.95
    気持ちを
    -1.91
    *}[
    -1.91
    陆续
    -1.91
     erfolgreichen
    -1.91
    瓩
    -1.89
    古い
    -1.88
     недавно
    -1.86
    POSITIVE LOGITS
    i
    2.39
    2
    2.31
     unſ
    2.30
     اذا
    2.14
    авто
    2.05
    3
    2.03
     để
    2.02
     bygge
    1.98
    to
    1.95
    0
    1.93
    Activations Density 0.011%

    No Known Activations