© 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. 70350
    Prev
    Next
    INDEX
    Explanations

    growth factors, configuration, route, 墙, Lawton

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

    This neuron is mainly detecting the character sequence “ong” in tokens (e.g. names like Truong, Phuong, 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
    閦
    -3.06
     unſ
    -3.05
    떳
    -2.59
    فقط
    -2.47
    ఙ
    -2.45
     มี
    -2.42
     tenemos
    -2.39
    𖣘
    -2.38
    艫
    -2.33
    ᾄ
    -2.31
    POSITIVE LOGITS
    ’
    3.20
    ;
    3.08
    “
    3.03
    .“
    2.77
     to
    2.61
     have
    2.58
    .”
    2.44
    …..
    2.44
    <td>
    2.33
    –
    2.33
    Activations Density 0.000%

    No Known Activations