© 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. 22-GEMMASCOPE-RES-131K
    4. 35756
    Prev
    Next
    INDEX
    Explanations

    title of

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

    The neuron fires strongly on tokens that are part of academic department affiliations (e.g. “Department of Physics” or “Department of Mathematics”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.62
    !
    -1.48
     that
    -1.47
    itisation
    -1.45
     their
    -1.38
    rably
    -1.35
     This
    -1.30
    fillment
    -1.26
    !」
    -1.25
     agreg
    -1.24
    POSITIVE LOGITS
     of
    1.84
    ,
    1.27
    GRAFÍA
    1.19
    rédients
    1.14
     美丽
    1.14
     盘
    1.13
    もあるので
    1.10
     码
    1.09
     erst
    1.08
     môžete
    1.07
    Activations Density 0.036%

    No Known Activations