© 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. 34-GEMMASCOPE-RES-131K
    7. 89830
    Prev
    Next
    INDEX
    Explanations

    coagulation or solidification

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

    words related to liquid or semi-liquid substances that can solidify or set.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to longer, content-rich tokens (e.g. multi-syllabic or technical words) rather than short or common words.

    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
    Kuva
    -0.83
    mjs
    -0.78
    Autore
    -0.71
     angeschlossen
    -0.71
     Lahore
    -0.70
    vage
    -0.70
     Correction
    -0.69
     dü
    -0.69
     abrasion
    -0.69
     suav
    -0.68
    POSITIVE LOGITS
     coag
    2.80
     clot
    2.53
     solidify
    2.48
     coagulation
    2.41
     solidified
    2.38
     solidif
    2.33
     soli
    2.30
     clotting
    2.22
    凝
    2.09
    soli
    2.08
    Activations Density 0.093%

    No Known Activations