© 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. 34-GEMMASCOPE-RES-131K
    7. 81111
    Prev
    Next
    INDEX
    Explanations

    carbonyl reduction

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

    programming language constructs and syntax across different languages like Haskell, Scala, SML, and functional programming concepts.

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

    This neuron responds to code-related tokens—programming language names, identifiers, and other programming‐jargon 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_34/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
    quisite
    -0.78
    APY
    -0.75
    耕
    -0.67
    gement
    -0.67
    agrama
    -0.67
    ruma
    -0.66
    ATTRIBUTES
    -0.66
    浚
    -0.65
     Loew
    -0.65
    readlines
    -0.65
    POSITIVE LOGITS
     reduction
    1.28
     reductions
    1.22
     Reduction
    1.17
    REDU
    1.14
     Redu
    1.11
     REDUCTION
    1.09
    Reduction
    1.08
     redu
    1.07
    redu
    1.06
     reducing
    1.05
    Activations Density 0.026%

    No Known Activations