© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    unab, unchecked, unfore, obo

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

    The neuron activates on the character sequence “obo” (i.e. it detects occurrences of “obo” inside words).

    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
    휀
    -2.83
    
    -2.80
    樒
    -2.47
    鸶
    -2.36
    )
    -2.36
    鉺
    -2.33
    makeat
    -2.27
     nome
    -2.25
    嵛
    -2.25
    觏
    -2.23
    POSITIVE LOGITS
    d
    3.08
    c
    2.56
    e
    2.39
    vač
    2.39
    eterangan
    2.22
    ++)
    2.19
    рации
    2.19
    and
    2.14
    tschaft
    2.13
    l
    2.13
    Activations Density 0.001%

    No Known Activations