© 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. 21357
    Prev
    Next
    INDEX
    Explanations

    om followed by specific terms

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

    The neuron flags tokens containing the letter sequence “om” (in any case), especially as part of acronyms or names.

    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
    墻
    -2.73
    i
    -2.58
     стоковые
    -2.55
    𓋼
    -2.53
     OGSÅ
    -2.38
    <bos>
    -2.36
    which
    -2.34
    ſſel
    -2.31
    atric
    -2.30
    these
    -2.27
    POSITIVE LOGITS
     –
    2.81
    {
    2.72
    结局
    2.58
    *
    2.36
    IN
    2.31
            
    2.28
     следующим
    2.27
     sickening
    2.27
     Obwohl
    2.22
    (
    2.22
    Activations Density 0.004%

    No Known Activations