© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67304
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron detects capitalized words and phrases that signal proper names (named entities).

    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
     "..\..\
    -1.88
    </u>
    -1.83
     "..\..\..\
    -1.74
    </b>
    -1.70
    ’,
    -1.67
    ‘
    -1.66
    ,”
    -1.63
    Does
    -1.55
    “,
    -1.52
    Ᏻ
    -1.52
    POSITIVE LOGITS
     then
    1.63
     respectivos
    1.61
     अलावा
    1.52
     '
    1.50
     has
    1.48
    拇
    1.47
     noticed
    1.47
     continue
    1.45
     abriu
    1.45
     servido
    1.45
    Activations Density 0.081%

    No Known Activations