© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41759
    Prev
    Next
    INDEX
    Explanations

    clínica, física, genéticalogía

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

    words for academic disciplines or fields of study in Romance languages, particularly ending in "ica" or similar suffixes.

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

    This neuron responds to multi-syllable technical or academic field names ending in the suffix “-ica” (or its orthographic variants, e.g. “-ika”).

    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
    '
    -2.28
     was
    -2.17
     milan
    -2.02
    !!!!
    -1.96
     —
    -1.93
    es
    -1.92
    !!!!!
    -1.91
     (‘
    -1.91
    ….
    -1.91
     –
    -1.88
    POSITIVE LOGITS
     geringen
    2.59
    .
    2.33
     tarefas
    2.33
     okno
    2.11
    🫅
    2.08
     Nuestros
    2.05
     évi
    2.03
     mesmas
    2.02
    Hmmm
    2.02
     Votre
    2.02
    Activations Density 0.036%

    No Known Activations