© 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. 71130
    Prev
    Next
    INDEX
    Explanations

    information and related phrases

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

    The neuron detects academic or technical context markers—multi-word phrases that introduce research background, challenges, problems, or interests (e.g. “background information,” “research interests,” “problem frequently encountered,” “scientific interest,” 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
    plasia
    -1.48
    CURLOPT
    -1.45
    THING
    -1.41
    gruss
    -1.40
    ziem
    -1.39
     },
    -1.37
     raio
    -1.36
    gruß
    -1.36
     kurios
    -1.31
    Viitteet
    -1.30
    POSITIVE LOGITS
     its
    1.68
     also
    1.59
    3
    1.57
     nevertheless
    1.53
     itself
    1.52
     nonetheless
    1.51
    1
    1.48
     still
    1.46
     therefore
    1.41
     также
    1.41
    Activations Density 0.155%

    No Known Activations