© 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. 127891
    Prev
    Next
    INDEX
    Explanations

    mini followed by another word

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

    The neuron is triggered by occurrences of the prefix “mini‐” (i.e. hyphenated “mini-” words indicating something small or short).

    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
    ߭
    -1.68
    *",
    -1.63
     to
    -1.62
    .
    -1.60
     Púb
    -1.56
    狍
    -1.52
     worin
    -1.51
     Referenzen
    -1.50
     Producción
    -1.49
     metrów
    -1.49
    POSITIVE LOGITS
     '
    1.83
     precioso
    1.65
    
    1.56
     suure
    1.53
    :"
    1.52
     hermoso
    1.52
     étrang
    1.51
    éreo
    1.51
    کاربرد
    1.50
    元々
    1.48
    Activations Density 0.017%

    No Known Activations