© 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. 19492
    Prev
    Next
    INDEX
    Explanations

    titles and roles

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

    The neuron fires strongly on editorial credit abbreviations (e.g. “ed.,” “eds.”) indicating it’s spotting references to editors.

    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
     our
    -1.88
     we
    -1.65
     nuestros
    -1.40
     to
    -1.39
     various
    -1.36
     nosso
    -1.31
     PUSTAKA
    -1.30
     posteriormente
    -1.25
     AppCompatTheme
    -1.25
     two
    -1.17
    POSITIVE LOGITS
    0
    1.44
    belline
    1.33
    最も
    1.33
     paraíso
    1.28
    such
    1.26
    cracy
    1.24
    phans
    1.21
    organism
    1.18
    onnaise
    1.17
    ーん
    1.16
    Activations Density 0.036%

    No Known Activations