© 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. 101677
    Prev
    Next
    INDEX
    Explanations

    double-blind studies

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

    technical terms in academic, scientific, or programming contexts.

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

    This neuron detects terminology related to study design and statistical reporting (e.g. “error bars,” “cumulatively,” “double-blind,” “randomly assigned,” etc.).

    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
     it
    -1.66
    ↵↵
    -1.58
     capucha
    -1.33
     pizarra
    -1.30
    始め
    -1.27
    тент
    -1.27
    YOND
    -1.26
    渙
    -1.25
     będzie
    -1.23
    寻求
    -1.23
    POSITIVE LOGITS
     as
    1.89
     from
    1.66
     on
    1.52
    €“
    1.41
    matisch
    1.38
    ;%%
    1.36
     něj
    1.34
     to
    1.33
    gingen
    1.31
    нии
    1.30
    Activations Density 0.086%

    No Known Activations