© 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. 49656
    Prev
    Next
    INDEX
    Explanations

    papillary, papilloma

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

    the term "papillary" or variations of "papilla" related to medical and anatomical structures.

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

    The neuron detects occurrences of the substring “pap” (e.g. in words like Paphos, papilla, papillary, etc.).

    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
    を
    -0.77
     interest
    -0.77
     บ
    -0.76
    ORA
    -0.72
     source
    -0.71
    Phong
    -0.70
     sure
    -0.69
    piston
    -0.69
    Interest
    -0.68
    tamanya
    -0.68
    POSITIVE LOGITS
     Pap
    1.16
    Pap
    1.13
     pap
    1.07
    pap
    0.88
     Gabor
    0.81
     smears
    0.81
    papar
    0.81
     pupa
    0.80
    äsche
    0.80
     Greco
    0.79
    Activations Density 0.025%

    No Known Activations