© 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. 34-GEMMASCOPE-RES-131K
    7. 58310
    Prev
    Next
    INDEX
    Explanations

    ND acronyms and abbreviations

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

    The neuron is detecting long substrings characteristic of specialized biochemical compound names (e.g. lipid or sphingolipid nomenclature).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     homicidio
    -0.75
    也在
    -0.72
    物
    -0.68
    rump
    -0.68
    팽
    -0.67
    liai
    -0.67
    nus
    -0.66
     isn
    -0.66
     Isn
    -0.66
     advierte
    -0.66
    POSITIVE LOGITS
     ND
    4.75
    ND
    4.53
     nd
    4.22
    nd
    3.48
     Nd
    3.41
    Nd
    3.25
     NDP
    2.92
     NDA
    2.86
     NDC
    2.80
     NDR
    2.52
    Activations Density 0.033%

    No Known Activations