© 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. 70833
    Prev
    Next
    INDEX
    Explanations

    import or use statements

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

    This neuron picks out numeric literal tokens (e.g. the multi‐digit line‐number–like values) 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_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
     новом
    -1.31
     белом
    -1.28
    batterie
    -1.26
    junge
    -1.25
    Detta
    -1.23
    serien
    -1.23
     magasiner
    -1.23
    teht
    -1.19
    terrasse
    -1.16
     triko
    -1.16
    POSITIVE LOGITS
    !
    1.08
    *
    1.05
    <strong>
    1.00
    <em>
    0.97
     время
    0.96
     cuándo
    0.95
    lfloor
    0.95
    닫
    0.94
    It
    0.94
    ほら
    0.94
    Activations Density 0.009%

    No Known Activations