© 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. 12679
    Prev
    Next
    INDEX
    Explanations

    overall [aspect/quality]

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

    The neuron reliably activates on the token “overall.”

    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
     of
    -2.22
     at
    -2.06
     in
    -2.06
     when
    -2.05
     for
    -2.00
     from
    -1.96
    )
    -1.84
     to
    -1.83
     with
    -1.83
     if
    -1.74
    POSITIVE LOGITS
     akumulator
    1.60
    AutoresizingMask
    1.56
     nostru
    1.51
     réinitial
    1.50
    ᗷ
    1.49
     Gefühle
    1.46
     Kampagne
    1.46
    プレート
    1.46
    を行い
    1.46
     correa
    1.45
    Activations Density 0.012%

    No Known Activations