© 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. 101757
    Prev
    Next
    INDEX
    Explanations

    dye-sensitized solar cells and LAMP assays

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

    scientific and technical terms in chemistry, biology, and physics, particularly focusing on specialized laboratory techniques and materials.

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

    The neuron detects highly technical scientific procedure or instrument terms (e.g. parts of method names or equipment acronyms).

    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
     these
    -1.44
     those
    -1.41
     hvad
    -1.30
     minimalista
    -1.20
    *_
    -1.16
    蔓延
    -1.16
    င်း
    -1.15
    валя
    -1.12
     the
    -1.11
    cristo
    -1.09
    POSITIVE LOGITS
    ])]
    1.39
    éta
    1.22
    円の
    1.21
    かえ
    1.20
    ']).
    1.18
     arrivo
    1.17
    而又
    1.16
    ප
    1.15
     aufgeführt
    1.15
     Sección
    1.13
    Activations Density 0.310%

    No Known Activations