© 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. 113006
    Prev
    Next
    INDEX
    Explanations

    things not widely known

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

    This neuron specifically activates on occurrences of the word “obscure.”

    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
    鈰
    -2.86
     It
    -2.81
     própri
    -2.45
     definiti
    -2.39
     diminu
    -2.36
    罍
    -2.34
    ・・・」
    -2.31
    泐
    -2.28
    をしていた
    -2.28
     唯美
    -2.28
    POSITIVE LOGITS
    ↵
    2.92
    𞤢
    2.86
     sebagainya
    2.42
    ’
    2.39
     były
    2.27
     $
    2.20
    ’;
    2.19
     eigenes
    2.19
    or
    2.16
     ganzes
    2.11
    Activations Density 0.003%

    No Known Activations