© 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. 10-GEMMASCOPE-RES-131K
    7. 39281
    Prev
    Next
    INDEX
    Explanations

    abi definitions and abbreviations

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

    The neuron fires whenever it encounters the token “ABI” (in any capitalization or as part of “abi”), i.e. references to the ABI acronym.

    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
    an
    -2.75
    ⩥
    -2.61
    麁
    -2.45
    脔
    -2.41
     wth
    -2.36
     =
    -2.30
    媗
    -2.30
    溆
    -2.27
    ly
    -2.23
    ++];
    -2.23
    POSITIVE LOGITS
     It
    2.42
    It
    2.20
     When
    2.19
    та
    2.14
    Let
    2.09
    Sometimes
    2.08
     Sometimes
    2.00
    Interestingly
    2.00
    There
    2.00
    At
    2.00
    Activations Density 0.004%

    No Known Activations