© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9832
    Prev
    Next
    INDEX
    Explanations

    Links and resources

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

    The neuron fires on section headers or titles that label lists of links or resources (e.g. “Links,” “Useful Links,” “Resources,” 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
    When
    -1.67
     if
    -1.60
    Because
    -1.59
     When
    -1.47
    If
    -1.45
     has
    -1.41
     Because
    -1.34
    シ
    -1.33
    =}
    -1.32
    摑
    -1.30
    POSITIVE LOGITS
     altes
    1.31
    跸
    1.26
    ieważ
    1.24
     deplorable
    1.23
     놀
    1.20
     båda
    1.20
    मेंट
    1.20
     blanches
    1.20
     languid
    1.19
     suoi
    1.18
    Activations Density 0.045%

    No Known Activations