© 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. 41271
    Prev
    Next
    INDEX
    Explanations

    posets, povidone, podiatrist

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

    This neuron strongly activates on the two‐letter sequence “po” (in any casing) whenever it appears as a token segment.

    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
    which
    -3.61
    un
    -3.36
    In
    -3.19
    us
    -3.14
    by
    -3.11
    H
    -3.11
    man
    -3.06
    .
    -2.98
    from
    -2.94
    C
    -2.89
    POSITIVE LOGITS
    
    3.64
    tedì
    3.05
    ichtete
    2.98
    𖣔
    2.75
     prostu
    2.75
    の絵
    2.69
    
    2.61
     tedy
    2.58
    沄
    2.58
     márm
    2.56
    Activations Density 0.004%

    No Known Activations