© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66226
    Prev
    Next
    INDEX
    Explanations

    Moderator, names, shallots

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

    The neuron activates on capitalized proper names (e.g. personal or character names).

    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
    ’
    -4.16
    $
    -2.86
     Они
    -2.58
     Also
    -2.55
    \\
    -2.45
    e
    -2.42
    it
    -2.41
    ),
    -2.39
    -2.36
    ”,
    -2.28
    POSITIVE LOGITS
     raiſ
    2.66
    ༀ
    2.55
    𖧵
    2.47
    ྂ
    2.31
    
    2.30
    ໊
    2.27
    ৢ
    2.27
    
    2.27
    涐
    2.23
    がない
    2.22
    Activations Density 0.003%
    No Known Activations