© 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. 10-GEMMASCOPE-RES-131K
    7. 130219
    Prev
    Next
    INDEX
    Explanations

    sham operations or deception

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

    The neuron flags mentions of “sham” (i.e. sham conditions, sham treatments, or placebo/control procedures).

    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
     The
    -2.80
     In
    -2.59
    $
    -2.58
     hiçbir
    -2.38
     enchanting
    -2.38
     finds
    -2.36
     smashing
    -2.34
     shattering
    -2.33
     al
    -2.31
     renuncia
    -2.28
    POSITIVE LOGITS
    ’
    3.41
    泺
    2.73
    媖
    2.42
    𞤢
    2.39
    廡
    2.34
    }}
    2.34
    縠
    2.34
    𐌺
    2.33
    ⢊
    2.33
     olie
    2.31
    Activations Density 0.002%

    No Known Activations