© 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. 43914
    Prev
    Next
    INDEX
    Explanations

    specialisation and specialty

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

    This neuron detects occurrences of words derived from “specialize”/“specialise” (e.g., specialization, specializing, speciality).

    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
    ارتمان
    -1.72
    </i>
    -1.72
    
    -1.71
    虓
    -1.66
    islamic
    -1.66
    槌
    -1.65
    护士
    -1.63
    znám
    -1.62
    唾
    -1.61
     You
    -1.59
    POSITIVE LOGITS
    type
    2.11
    d
    1.95
     الرئيسي
    1.85
    7
    1.84
    if
    1.82
    3
    1.81
    my
    1.78
    end
    1.78
    after
    1.78
    4
    1.75
    Activations Density 0.026%

    No Known Activations