© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101272
    Prev
    Next
    INDEX
    Explanations

    moving from

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

    The neuron detects words and phrases that express ability or capability (e.g. “capable of …” and “able 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
     also
    -1.23
    URATION
    -1.21
     также
    -1.20
     myös
    -1.19
     tampoco
    -1.12
    ⻓
    -1.11
     también
    -1.10
     також
    -1.08
     גם
    -1.08
     destaque
    -1.04
    POSITIVE LOGITS
    1.27
    1.20
    ramid
    1.03
     bowiem
    1.00
    fraid
    0.98
     everything
    0.95
    нева
    0.95
    vece
    0.94
     définiti
    0.94
    telling
    0.94
    Activations Density 1.189%

    No Known Activations