© 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. 10-GEMMASCOPE-RES-131K
    7. 90807
    Prev
    Next
    INDEX
    Explanations

    find detailed product

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

    The neuron fires on calls-to-action inviting the reader to “find more” (e.g. “find…more”) or similar link‐prompting phrasing.

    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
     three
    -1.71
    When
    -1.61
     just
    -1.60
     ostensibly
    -1.52
     five
    -1.52
     When
    -1.45
     because
    -1.42
    when
    -1.41
     .....
    -1.41
     demonstrating
    -1.38
    POSITIVE LOGITS
     detenidos
    1.53
    壅
    1.49
     on
    1.49
     conciertos
    1.41
    囮
    1.39
    plante
    1.36
    sproble
    1.35
     humaine
    1.34
    摄像
    1.32
     формирования
    1.31
    Activations Density 0.077%

    No Known Activations