© 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. 15388
    Prev
    Next
    INDEX
    Explanations

    trying to

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

    The neuron activates on action verbs (e.g. won, born, involve) wherever they occur.

    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
    ,
    -1.48
     other
    -1.22
     what
    -1.20
     which
    -1.17
     hvis
    -1.15
    諾
    -1.13
     more
    -1.10
     ,
    -1.09
    }
    -1.08
    från
    -1.06
    POSITIVE LOGITS
     also
    2.83
     также
    2.47
     también
    2.31
     também
    2.19
     також
    2.11
     cũng
    2.09
     myös
    2.09
     également
    2.06
    also
    2.03
     także
    2.03
    Activations Density 0.533%

    No Known Activations