© 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. 67280
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

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

    The neuron is effectively “dead” in these examples—it never produces any nonzero activation and thus isn’t detecting any particular pattern.

    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
    、
    -1.09
    ⿳
    -1.05
     decorativos
    -1.05
     nowy
    -1.02
    äne
    -1.02
    を
    -1.00
     друзей
    -0.95
     двигатель
    -0.95
     konkret
    -0.95
     nazwa
    -0.95
    POSITIVE LOGITS
    Ingredi
    1.24
    Seni
    1.21
    ※※
    1.20
    －－－－
    1.13
     hauptsächlich
    1.07
    مقدمه
    1.06
     Usually
    1.05
    when
    1.05
    取締
    1.05
    Hadi
    1.05
    Activations Density 0.022%

    No Known Activations