© 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. 22-GEMMASCOPE-RES-131K
    4. 27939
    Prev
    Next
    INDEX
    Explanations

    hypoxic, teeth, DNA, water, growth factor

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

    The neuron identifies numerical values, dates, and measurements in academic or reference text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     sukienka
    -1.19
     только
    -1.18
    UNIDENTIFIED
    -1.17
     zimowa
    -1.15
     In
    -1.15
     później
    -1.13
     фаса
    -1.12
     ^{-
    -1.12
     or
    -1.09
    Ако
    -1.07
    POSITIVE LOGITS
     psychiat
    1.32
     sembla
    1.26
     tâ
    1.20
    
    1.20
     aussit
    1.16
     indispensables
    1.14
     entrées
    1.13
     châ
    1.11
     plafon
    1.11
     râ
    1.10
    Activations Density 0.093%

    No Known Activations