© 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. 14276
    Prev
    Next
    INDEX
    Explanations

    flute, VHF, gourd, page

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

    The neuron detects words beginning with the letter sequence “flu,” such as flute, fluted, fluting, etc.

    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
    
    -2.66
    々木
    -2.66
     egregious
    -2.45
     باسلام
    -2.44
    ஂ
    -2.36
     هناك
    -2.34
    เกง
    -2.34
    瑧
    -2.33
    istocene
    -2.33
     в
    -2.33
    POSITIVE LOGITS
    𓋼
    3.59
    2.30
    </i>
    2.30
    鹪
    2.25
    鯓
    2.23
    And
    2.22
     It
    2.17
     jis
    2.16
     öst
    2.13
     feroit
    2.13
    Activations Density 0.003%
    No Known Activations