© 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. 7233
    Prev
    Next
    INDEX
    Explanations

    phon, phono stems

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

    The neuron is highly activated by any occurrence of the character sequence “phon” (as in phonon, phoneme, phonation, phonological, 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
    .”
    -3.22
    which
    -2.63
     Of
    -2.41
     達
    -2.34
    !”
    -2.34
     mientras
    -2.33
    they
    -2.25
     imidlertid
    -2.14
    We
    -2.14
    ⤞
    -2.13
    POSITIVE LOGITS
     grü
    2.61
    {
    2.31
     gewiß
    2.31
     grün
    2.28
     keker
    2.27
     majú
    2.23
    個人的に
    2.20
     dasarnya
    2.17
     trocken
    2.13
    摠
    2.09
    Activations Density 0.005%

    No Known Activations