© 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. 75455
    Prev
    Next
    INDEX
    Explanations

    lists of topics

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

    The neuron detects section headings or titles (e.g. capitalized phrases introducing a new section, often ending with a colon or question mark).

    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
     -
    -2.05
     was
    -1.85
     of
    -1.70
     [
    -1.62
    %
    -1.61
    '
    -1.59
    an
    -1.58
     --
    -1.57
    "
    -1.57
    )
    -1.56
    POSITIVE LOGITS
     you
    1.87
     tega
    1.85
     stolet
    1.78
     šte
    1.75
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.74
     ujedno
    1.69
     acompañado
    1.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.66
     drugim
    1.63
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.63
    Activations Density 0.015%

    No Known Activations