© 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. 10-GEMMASCOPE-RES-131K
    7. 44679
    Prev
    Next
    INDEX
    Explanations

    Observer and observer pattern

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

    The neuron activates on occurrences of the identifier “Observer” (e.g. class or variable names containing “Observer”).

    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
    )
    -2.88
     was
    -2.84
    1
    -2.63
    没有
    -2.63
    3
    -2.50
     vorigen
    -2.47
    5
    -2.47
    2
    -2.45
     organisiert
    -2.27
     schlechte
    -2.27
    POSITIVE LOGITS
    铪
    3.16
    錞
    2.78
    鯢
    2.75
     preferido
    2.63
     MessageBoxIcon
    2.50
    ❉
    2.44
    ቍ
    2.41
    镚
    2.38
    ⼗
    2.38
    櫪
    2.33
    Activations Density 0.003%

    No Known Activations