© 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. 98640
    Prev
    Next
    INDEX
    Explanations

    common code identifiers

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

    The neuron fires on code identifier tokens—that is, variable and object names in source 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
     Kullan
    -1.20
     Wiktionnaire
    -1.18
    腱
    -1.05
    anız
    -1.04
    ᅲ
    -1.03
     szolgált
    -1.02
    tuig
    -1.02
     while
    -1.02
     of
    -0.99
     jenis
    -0.99
    POSITIVE LOGITS
     abend
    1.07
     haup
    0.98
     bloss
    0.97
    ちなみに
    0.96
     zoll
    0.95
    ⩾
    0.94
    ([
    0.94
    有一些
    0.94
    つまり
    0.93
    .
    0.93
    Activations Density 0.008%

    No Known Activations