© 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. 10-GEMMASCOPE-RES-131K
    4. 87377
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

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

    The neuron fires on numeric “0” tokens (e.g. the digit 0 appearing in CSS values or hex codes).

    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
    .
    -1.58
     pasaran
    -1.43
     nuestras
    -1.36
     películas
    -1.34
     beeintr
    -1.34
     ruined
    -1.33
     piezas
    -1.33
    τας
    -1.32
    biotics
    -1.30
     völlig
    -1.29
    POSITIVE LOGITS
     either
    1.48
     then
    1.48
     conting
    1.38
     их
    1.37
    ARING
    1.32
     той
    1.31
     گرف
    1.30
    presumably
    1.29
    ñor
    1.24
    Dě
    1.23
    Activations Density 0.003%

    No Known Activations