© 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. 22-GEMMASCOPE-RES-131K
    7. 26810
    Prev
    Next
    INDEX
    Explanations

    papillomavirus

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

    medical/scientific content about human papillomavirus (HPV) and associated medical conditions.

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

    The neuron detects occurrences of “human papillomavirus” (HPV)–related terms (e.g. pap, illoma, virus, HPV).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     mendes
    -1.13
     braun
    -1.13
     jų
    -1.12
     upacara
    -1.09
     Newborn
    -1.08
     hemd
    -1.07
     velours
    -1.06
     बजाय
    -1.06
    ốm
    -1.06
     kvinna
    -1.05
    POSITIVE LOGITS
     leta
    1.12
    ך
    1.06
     рассматри
    1.05
     protège
    1.05
    目を
    1.02
     risk
    0.98
     caveat
    0.98
     Freunden
    0.96
    莅
    0.94
    مصادر
    0.93
    Activations Density 0.269%

    No Known Activations