© 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. 38744
    Prev
    Next
    INDEX
    Explanations

    Ava, seaweed, Scy, clearfix

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

    The neuron strongly fires on any token containing the character sequence “ava.”

    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
    That
    -2.64
    _
    -2.47
     definately
    -2.38
    Maybe
    -2.28
    大多数
    -2.16
    Although
    -2.16
    Despite
    -2.14
     ответить
    -2.13
     NEVER
    -2.13
    ться
    -2.13
    POSITIVE LOGITS
    쨩
    2.61
    ?”
    2.52
    ѣмъ
    2.48
    ⚣
    2.39
    ხ
    2.39
    
    2.28
    鷙
    2.27
    鮰
    2.25
    ⢅
    2.23
    
    2.22
    Activations Density 0.005%

    No Known Activations