© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1532
    Prev
    Next
    INDEX
    Explanations

    PHPUnit usage

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

    This neuron responds specifically to the Japanese kanji “初” (meaning “first” or “beginning”).

    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
     "
    -3.45
     The
    -3.20
    </b>
    -3.16
       
    -2.70
     You
    -2.63
     Because
    -2.63
      
    -2.61
    -"
    -2.58
     Would
    -2.55
    </td>
    -2.53
    POSITIVE LOGITS
    衕
    3.20
    )";
    3.08
    鉺
    2.75
    F
    2.72
    StoryboardSegue
    2.70
    馘
    2.70
    ⸰
    2.69
    ized
    2.69
    🩻
    2.69
     INDEP
    2.67
    Activations Density 0.000%

    No Known Activations