© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22123
    Prev
    Next
    INDEX
    Explanations

    meningitis, potentials, respiratory, efficacy

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

    the suffix "-ial" in medical and technical terms.

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

    The neuron fires on words ending in the “-ial” (or “-tial”) suffix—for example nosocomial, arterial, and potential.

    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
    楙
    -2.61
    ㈦
    -2.59
     gevaar
    -2.42
    媜
    -2.38
    ühner
    -2.36
     marquées
    -2.34
    难怪
    -2.31
    ettür
    -2.28
    цию
    -2.27
    cristo
    -2.27
    POSITIVE LOGITS
    3
    3.53
    7
    3.28
    9
    2.98
    6
    2.95
    isation
    2.94
    ized
    2.92
    4
    2.92
    8
    2.91
    ist
    2.81
    ial
    2.81
    Activations Density 0.026%

    No Known Activations