© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72386
    Prev
    Next
    INDEX
    Explanations

    acclaim, 見えます

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

    The neuron fires on mentions of simple inanimate systems (e.g. “thermostat” or “toaster”) used as contrasts to sentient organisms.

    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
    罒
    -1.12
    årige
    -1.09
     with
    -1.07
    4
    -1.02
     Schrifts
    -0.97
    ılığı
    -0.94
     smör
    -0.94
    بالإ
    -0.94
    álna
    -0.93
     reveló
    -0.93
    POSITIVE LOGITS
    ఱ
    1.13
     "
    1.03
    見えます
    0.98
     acclaim
    0.98
    0.95
    핌
    0.92
     frattempo
    0.91
    
    0.91
    R
    0.91
     paraly
    0.90
    Activations Density 0.045%

    No Known Activations