© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129343
    Prev
    Next
    INDEX
    Explanations

    the rest of

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

    This neuron detects references to the “rest of” or remaining portion of content (e.g. “the rest of the species,” “the rest of the document,” “the rest of this dialog,” etc.).

    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
     as
    -1.62
    Producción
    -1.41
     and
    -1.39
     juuri
    -1.32
    Another
    -1.29
    ῶν
    -1.28
    ámicas
    -1.28
    tät
    -1.27
    وازم
    -1.27
    Here
    -1.27
    POSITIVE LOGITS
    ↵
    1.90
     pleaf
    1.35
     occaf
    1.34
     poffe
    1.33
     occafion
    1.29
     neceff
    1.23
     prevista
    1.23
     previsto
    1.23
     fubject
    1.23
     остальные
    1.20
    Activations Density 0.019%

    No Known Activations