© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113490
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers

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

    opening quotation marks or apostrophes in code that begin string literals.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron responds to quoted string literals (i.e. tokens marking or inside a string literal).

    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
    了不少
    -1.52
     more
    -1.50
     säll
    -1.49
     When
    -1.48
     was
    -1.44
    樁
    -1.41
     erläut
    -1.38
     zostać
    -1.37
    When
    -1.37
     where
    -1.37
    POSITIVE LOGITS
     suche
    1.42
     itp
    1.39
    mogen
    1.36
    NYA
    1.34
     mei
    1.34
     介绍
    1.34
    첵
    1.34
     jon
    1.34
     anty
    1.33
    mă
    1.31
    Activations Density 0.000%

    No Known Activations