© 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. 67189
    Prev
    Next
    INDEX
    Explanations

    texture sampling and coordinates

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

    The neuron strongly fires on code tokens having to do with texture resources—e.g. “texture,” “TEXTURE,” “TEXCOORD,” “sampler2D,” and similar texture‐related identifiers in shader or graphics code.

    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
    7
    -1.39
     läßt
    -1.29
    .”
    -1.24
     and
    -1.21
     Your
    -1.19
    ”
    -1.17
    }$,
    -1.15
     sekitar
    -1.13
    ithe
    -1.13
    9
    -1.13
    POSITIVE LOGITS
    Bjs
    1.38
     neust
    1.16
     mélang
    1.14
    Volley
    1.13
     copyrights
    1.13
    次数
    1.13
    理会
    1.12
    哢
    1.12
     realise
    1.11
     ссылка
    1.11
    Activations Density 0.015%

    No Known Activations