© 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. 22-GEMMASCOPE-RES-131K
    7. 13905
    Prev
    Next
    INDEX
    Explanations

    check out the FAQ by clicking the link

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

    The neuron fires on structural punctuation and delimiter tokens—e.g. XML/HTML tag brackets (>, </), slashes, parentheses, punctuation marks, and similar non-word symbols.

    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
    breviations
    -1.12
     wanneer
    -1.05
     лютого
    -1.05
    grees
    -1.01
     if
    -0.97
     यदि
    -0.95
     said
    -0.92
    回戦
    -0.91
     октября
    -0.91
    eronau
    -0.89
    POSITIVE LOGITS
    Willkommen
    1.23
    Frage
    1.09
    Tania
    1.06
    Einfach
    1.05
    Moda
    1.04
    EVALU
    1.03
    Reduc
    1.02
    INGREDIENT
    1.02
    Herzlich
    1.02
    Impressum
    0.99
    Activations Density 0.023%

    No Known Activations