© 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. 34-GEMMASCOPE-RES-131K
    4. 83206
    Prev
    Next
    INDEX
    Explanations

    water and saline solutions

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

    instances of liquids like water or solutions being used in scientific procedures or recipes.

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

    The neuron detects numeric tokens or numeric expressions (digits or numbers) within the text.

    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
     çik
    -0.84
    MessageBox
    -0.78
    हाँ
    -0.77
     docx
    -0.77
    tsy
    -0.77
    evich
    -0.75
    liquid
    -0.75
     liquidation
    -0.75
    cises
    -0.74
    鉀
    -0.74
    POSITIVE LOGITS
     distilled
    1.34
     water
    1.26
     tap
    1.07
     fresh
    1.01
     warm
    0.99
     pure
    0.99
     plain
    0.91
     cold
    0.82
     potable
    0.82
    纯
    0.82
    Activations Density 0.037%

    No Known Activations