© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6382
    Prev
    Next
    INDEX
    Explanations

    genital anatomy

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

    The neuron is detecting numeric tokens and quantitative measurements (e.g. decimal numbers, dosages, counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metabolic
    0.57
    夋
    0.56
    代谢
    0.54
     डेंगू
    0.52
     transgenic
    0.52
     PCBs
    0.51
     glucocortic
    0.51
    肋
    0.51
     consolid
    0.50
     تغ
    0.50
    POSITIVE LOGITS
     vaginal
    1.53
     vagina
    1.52
     urethra
    1.49
    膣
    1.40
     vaginale
    1.36
     ureth
    1.32
    腟
    1.30
     cervix
    1.29
     penile
    1.24
     penis
    1.23
    Activations Density 0.264%

    No Known Activations