© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10945
    Prev
    Next
    INDEX
    Explanations

    val and value

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

    The neuron fires over numeric literal tokens (e.g. integer or floating-point constants) 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_10/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
     of
    -1.63
     that
    -1.54
    )
    -1.20
    ご覧
    -1.19
    回想
    -1.15
     Their
    -1.14
    作为
    -1.13
    近年
    -1.12
    ,<
    -1.12
    .”
    -1.10
    POSITIVE LOGITS
    摟
    1.45
     saca
    1.42
    bria
    1.38
    摇了
    1.36
    yadh
    1.31
    すぎた
    1.29
    </strong>
    1.27
    驮
    1.25
    拦
    1.23
    reador
    1.22
    Activations Density 0.025%

    No Known Activations