© 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. 87146
    Prev
    Next
    INDEX
    Explanations

    aba or ava sequences

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

    The neuron responds specifically to the three‐letter sequence “aba” appearing anywhere within a token.

    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
    '
    -2.88
    ikusbot
    -2.75
    殽
    -2.48
    "
    -2.33
    ing
    -2.31
    ');
    -2.28
    的问道
    -2.22
    是你
    -2.14
    -2.14
     pensar
    -2.13
    POSITIVE LOGITS
    蕯
    2.52
    釙
    2.41
     certaine
    2.36
    aderos
    2.27
     Roughly
    2.23
     від
    2.17
    鯷
    2.17
     immaculate
    2.16
    ستارهای
    2.13
     rejuven
    2.11
    Activations Density 0.019%
    No Known Activations