© 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. 104336
    Prev
    Next
    INDEX
    Explanations

    various contexts

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

    The neuron identifies the central content words (key technical or topic-specific terms) in a question.

    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
     хорошо
    -1.15
    新宿
    -1.07
    ◆◆
    -1.06
    <bos>
    -1.02
    曺
    -1.02
    gä
    -1.01
     getting
    -1.01
     helping
    -1.00
     oftentimes
    -0.98
     который
    -0.98
    POSITIVE LOGITS
    without
    1.50
     without
    1.29
     ohne
    1.25
     hanya
    1.15
     same
    1.12
     via
    1.11
     with
    1.09
     differently
    1.08
     instead
    1.04
     zonder
    1.02
    Activations Density 0.107%

    No Known Activations