© 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. 20063
    Prev
    Next
    INDEX
    Explanations

    of the last century

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

    The neuron activates on the main action verbs (the core predicate) in a sentence.

    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
     både
    -1.65
     zowel
    -1.51
    keine
    -1.48
    lllllll
    -1.47
    große
    -1.38
     zarówno
    -1.38
     tada
    -1.34
    ﹎
    -1.34
    Ꮗ
    -1.34
    裥
    -1.31
    POSITIVE LOGITS
     of
    1.79
     different
    1.59
     like
    1.59
     still
    1.49
     ancora
    1.48
     moves
    1.48
     meistens
    1.48
    ),
    1.48
    なんだけど
    1.46
     zabur
    1.46
    Activations Density 0.001%

    No Known Activations