© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45534
    Prev
    Next
    INDEX
    Explanations

    example of

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

    The neuron fires on the phrasing that introduces illustrative examples (e.g. “example,” “an example of,” “examples include”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    解説
    -1.07
     electricidad
    -1.05
    ÉM
    -1.05
     sillas
    -1.03
    BIND
    -1.02
    ﺼ
    -1.01
    helves
    -1.00
    omeness
    -0.99
     gasolina
    -0.98
     lakukan
    -0.98
    POSITIVE LOGITS
     of
    5.50
    ของ
    1.58
     where
    1.57
     thereof
    1.29
     из
    1.18
     hereof
    1.11
     from
    1.01
    of
    0.99
     того
    0.97
     cotidiano
    0.96
    Activations Density 0.029%

    No Known Activations