© 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. 34-GEMMASCOPE-RES-131K
    7. 32416
    Prev
    Next
    INDEX
    Explanations

    erection and hardness

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

    content related to sexual arousal and erectile function.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect explicit sexual arousal language and graphic erotic terms.

    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
    uther
    -0.75
    ҃
    -0.74
    육
    -0.72
    bihi
    -0.71
    hastly
    -0.71
    ánh
    -0.71
    setCellStyle
    -0.71
    Gall
    -0.70
    Memphis
    -0.69
     Tân
    -0.68
    POSITIVE LOGITS
     erection
    1.79
     erect
    1.40
     hard
    1.38
     arousal
    1.38
     aroused
    1.37
     hardness
    1.27
    hard
    1.19
     harder
    1.16
    勃
    1.15
     harden
    1.14
    Activations Density 0.048%

    No Known Activations