© 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. 22-GEMMASCOPE-RES-131K
    7. 65342
    Prev
    Next
    INDEX
    Explanations

    code parameters/identifiers

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

    This neuron detects the opening quotation mark of a string literal (i.e. the quote character that begins a literal in code).

    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
     (
    -1.09
    silian
    -1.00
     tény
    -0.97
    
    -0.96
     our
    -0.94
     powietrza
    -0.93
     okresie
    -0.93
    rairie
    -0.92
     «
    -0.91
     en
    -0.90
    POSITIVE LOGITS
    Transk
    1.32
    Beskrivelse
    1.17
    Приготовление
    1.13
     gustó
    1.11
    Inhalts
    1.09
    Publié
    1.07
    توضیحات
    1.06
    mę
    1.05
    雖然
    1.05
     аккура
    1.05
    Activations Density 0.018%

    No Known Activations