© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99888
    Prev
    Next
    INDEX
    Explanations

    pre and post prefixes

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

    The neuron activates on the subword pieces of hyphenated compounds (especially prefixes like “pre-” and “post-” and their adjoining segments).

    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
     incluyendo
    -0.85
    omaterial
    -0.71
     permitiendo
    -0.70
     inicialmente
    -0.70
     refuer
    -0.68
    ikiki
    -0.68
     Ser
    -0.67
     thưởng
    -0.67
     Col
    -0.66
    cull
    -0.66
    POSITIVE LOGITS
    __.
    0.93
     adoptive
    0.82
     uur
    0.82
    ☹
    0.79
    рама
    0.79
    başı
    0.79
     implique
    0.78
    graduate
    0.77
    Answers
    0.77
    мите
    0.77
    Activations Density 0.051%

    No Known Activations