© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84100
    Prev
    Next
    INDEX
    Explanations

    pretty wedding dresses

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

    The neuron is selectively activating on non‐word formatting and markup symbols (like asterisks, angle‐bracket tags, and similar punctuation used for annotations).

    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
     kuhusu
    -1.06
    を使って
    -0.99
     inaweza
    -0.96
     muhimu
    -0.95
     nzuri
    -0.91
     maisha
    -0.91
    anud
    -0.89
     ambao
    -0.87
     utaf
    -0.87
     listened
    -0.86
    POSITIVE LOGITS
     and
    1.05
    ioutil
    1.03
    💑
    0.89
    烨
    0.88
     künf
    0.88
    斗争
    0.88
    ЦИИ
    0.87
     TextAlign
    0.86
    richtet
    0.85
     eventuell
    0.84
    Activations Density 0.002%

    No Known Activations