© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13853
    Prev
    Next
    INDEX
    Explanations

    acid

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

    The neuron detects the word "acid" and related chemical terms in scientific contexts.

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

    The main thing this neuron does is detect occurrences of the substring “acid” in words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    I
    -2.77
    やう
    -2.53
    さに
    -2.44
    世上
    -2.44
    だけど
    -2.39
     ‘’
    -2.33
    嵓
    -2.33
    缐
    -2.28
    丏
    -2.28
    ,’’
    -2.23
    POSITIVE LOGITS
     \&
    2.83
    牁
    2.47
     ouvrage
    2.44
    perusahaan
    2.33
    ării
    2.31
     две
    2.31
    lässlich
    2.30
    𝟏
    2.20
    ᥫ
    2.19
    一番
    2.17
    Activations Density 0.026%

    No Known Activations