© 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. 10-GEMMASCOPE-RES-131K
    7. 59747
    Prev
    Next
    INDEX
    Explanations

    borderline hypertension personality disorder

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

    The neuron selectively responds to occurrences of words containing the root “border” (e.g. “borderline,” “bordering”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     There
    -2.16
     “
    -2.09
     droom
    -2.06
    鬭
    -2.05
     Get
    -2.03
     Color
    -2.03
    王爷
    -2.00
     The
    -1.91
    nél
    -1.91
    ,
    -1.84
    POSITIVE LOGITS
    ،
    2.81
    3
    2.72
    up
    2.69
    䊏
    2.58
    䊐
    2.48
    潆
    2.47
    ."
    2.39
    ?"
    2.19
    *,
    2.14
    我只
    2.13
    Activations Density 0.005%

    No Known Activations