© 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. 43964
    Prev
    Next
    INDEX
    Explanations

    pot prefix

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

    This neuron activates on occurrences of words beginning with the letter sequence “pot.”

    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
    was
    -3.05
    on
    -2.56
    hhh
    -2.36
    irs
    -2.34
    hhhh
    -2.33
    ve
    -2.22
    be
    -2.22
    谖
    -2.20
    鏨
    -2.19
    would
    -2.17
    POSITIVE LOGITS
    </strong>
    3.28
    鉏
    2.61
    migiano
    2.39
    ᷆
    2.39
    ramide
    2.38
     podem
    2.33
     was
    2.33
    viedo
    2.31
     owing
    2.30
    mazioni
    2.27
    Activations Density 0.009%

    No Known Activations