© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66735
    Prev
    Next
    INDEX
    Explanations

    XML structure and foreign languages

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

    The neuron never fires—it does not detect any patterns in the input.

    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
    を
    -1.57
     in
    -1.30
    ・・・」
    -1.30
    子を
    -1.29
    ！！」
    -1.25
    子は
    -1.24
     know
    -1.24
     Ș
    -1.23
    しと
    -1.23
     extenso
    -1.21
    POSITIVE LOGITS
    了不少
    1.41
     probablemente
    1.40
    様な
    1.35
     protože
    1.35
     geliefert
    1.34
    向けの
    1.30
     stattfinden
    1.28
    為に
    1.28
     seguramente
    1.27
    :
    1.26
    Activations Density 0.010%

    No Known Activations