© 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. 130805
    Prev
    Next
    INDEX
    Explanations

    The neuron signals on double‐quote characters marking string or character literals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    questions starting with q followed by a colon

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     onOptions
    -1.24
    ciptakan
    -1.21
    :✨
    -1.16
    齟
    -1.15
     requer
    -1.12
    Edith
    -1.11
     extenso
    -1.11
     itens
    -1.10
    AppRoutingModule
    -1.09
     sagrada
    -1.09
    POSITIVE LOGITS
     and
    1.38
     ovviamente
    1.31
     alimentare
    1.28
     we
    1.24
     niedersachsen
    1.17
     erhi
    1.16
     marchandises
    1.16
     Privac
    1.16
     Matériau
    1.16
    が見える
    1.16
    Activations Density 0.000%

    No Known Activations