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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67022
    Prev
    Next
    INDEX
    Explanations

    filament

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

    This neuron activates on occurrences of the substring “filament” (e.g. “filament,” “filamentous”) in the text.

    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
    ”、“
    -2.67
    倨
    -2.50
    路的
    -2.42
    銥
    -2.39
    价比
    -2.39
     multitude
    -2.38
    𞤢
    -2.36
     unglaub
    -2.36
    ❉
    -2.34
    塬
    -2.33
    POSITIVE LOGITS
     For
    2.75
    </i>
    2.73
     สำหรับ
    2.70
    </h3>
    2.56
    鸸
    2.39
     harán
    2.34
    “
    2.34
     respecting
    2.33
     kurzem
    2.20
    ны
    2.19
    Activations Density 0.005%

    No Known Activations