© 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. 34-GEMMASCOPE-RES-131K
    7. 78965
    Prev
    Next
    INDEX
    Explanations

    naked or nude

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

    The neuron strongly activates on occurrences of the word “Naked” (and closely related synonyms like “bare”).

    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
    一下子
    -0.83
     источник
    -0.81
    шенные
    -0.80
    ISODE
    -0.79
    噉
    -0.77
     الأح
    -0.74
     unbelie
    -0.74
     worth
    -0.74
     Toulon
    -0.74
    ("#
    -0.73
    POSITIVE LOGITS
    naked
    1.43
    Naked
    1.39
     naked
    1.33
     bare
    1.28
    裸
    1.19
     Naked
    1.14
     truth
    1.13
    truth
    1.10
    bare
    1.02
     Truth
    1.02
    Activations Density 0.018%

    No Known Activations