© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116564
    Prev
    Next
    INDEX
    Explanations

    what can be done

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

    The neuron detects expressions of possibility or ability—phrases like “can do,” “do anything,” or “can be done.”

    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
    TASKS
    -0.98
    Bram
    -0.90
     funkcji
    -0.88
    searchBar
    -0.84
     FUNCTIONS
    -0.84
    Kde
    -0.82
    SUCCEEDED
    -0.81
    ایل
    -0.80
    IZES
    -0.79
     accomplishments
    -0.79
    POSITIVE LOGITS
     about
    1.34
     to
    1.09
     do
    0.99
    ช่วย
    0.94
     solution
    0.94
     can
    0.92
     done
    0.90
    怎麼辦
    0.90
     measures
    0.90
     solutions
    0.85
    Activations Density 0.031%

    No Known Activations