© 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. 39276
    Prev
    Next
    INDEX
    Explanations

    Alibaba and fairy tale characters

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

    The neuron chiefly picks out prominent proper nouns or titles (e.g. brand names, personal names, article titles).

    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
    檍
    -1.92
    re
    -1.84
    蕷
    -1.82
    en
    -1.81
    謦
    -1.77
    ｌ
    -1.75
    izoen
    -1.74
    tså
    -1.73
    螓
    -1.68
    ebly
    -1.65
    POSITIVE LOGITS
    ’
    1.70
     &
    1.66
     Aladdin
    1.63
    pantaloni
    1.52
     où
    1.48
    ные
    1.46
    Aladdin
    1.42
    cloudf
    1.41
     gevoel
    1.41
    louis
    1.40
    Activations Density 0.008%

    No Known Activations