© 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. 116840
    Prev
    Next
    INDEX
    Explanations

    Field of the Disclosure

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

    The neuron flags programming‐style tokens—e.g. identifiers or namespace operators (underscores, “::”, etc.)—that occur in code snippets.

    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
     this
    -1.23
     at
    -1.19
     which
    -1.11
     on
    -1.09
    After
    -1.08
     from
    -1.07
    Shortly
    -1.06
     frantic
    -1.01
     Usually
    -0.98
     after
    -0.97
    POSITIVE LOGITS
    referred
    1.14
    basically
    1.07
    expressed
    1.01
     accentu
    1.01
     praticamente
    0.99
    five
    0.98
     Mã
    0.97
    perhaps
    0.97
    やかに
    0.96
    owanie
    0.95
    Activations Density 0.004%

    No Known Activations