© 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. 99484
    Prev
    Next
    INDEX
    Explanations

    actions taken towards a goal

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

    This neuron activates on occurrences of the word “effort” (especially in the phrase “efforts to …”).

    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
    sätzlich
    -1.94
     plainte
    -1.88
    臏
    -1.80
     êtres
    -1.73
    鱚
    -1.70
    ↓↓↓
    -1.70
     ſch
    -1.70
    二日
    -1.69
    初めての
    -1.66
    críbete
    -1.65
    POSITIVE LOGITS
     to
    2.56
    ↵↵
    2.06
    s
    1.86
     Its
    1.82
    us
    1.82
    n
    1.81
    ),
    1.78
    DANGER
    1.70
    urs
    1.69
     effort
    1.66
    Activations Density 0.023%

    No Known Activations