© 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. 85580
    Prev
    Next
    INDEX
    Explanations

    speaking, saying, or explaining

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

    The neuron flags words that denote speaking or expressing something aloud (e.g. say, loud, voice, explain, recount, tweet).

    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
     each
    -1.16
    小编
    -1.14
    秆
    -1.13
    hueta
    -1.12
    PullParser
    -1.12
     we
    -1.11
     dió
    -1.10
     distinguir
    -1.09
    letcher
    -1.06
    да
    -1.05
    POSITIVE LOGITS
     to
    2.48
     sebuah
    1.20
     piatta
    1.19
     şeyi
    1.17
     or
    1.16
    spod
    1.16
     Noviembre
    1.13
    Reak
    1.13
    ώ
    1.11
     frattempo
    1.10
    Activations Density 0.140%

    No Known Activations