© 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. 34-GEMMASCOPE-RES-131K
    7. 2840
    Prev
    Next
    INDEX
    Explanations

    wielding weapons or skills

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

    This neuron detects hyphenated compound verbs that describe weapon use (e.g. “dual-wielding,” “plasmid-wielding,” “gun-toting”).

    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
    ínico
    -0.71
    放在
    -0.68
    ït
    -0.66
     Roskov
    -0.66
     dictionary
    -0.65
     وت
    -0.65
    وجود
    -0.65
    طريقة
    -0.64
    phosp
    -0.64
     словарь
    -0.64
    POSITIVE LOGITS
     wield
    4.19
     wielding
    4.06
     wiel
    3.47
     wielded
    3.42
    ield
    1.68
     yielding
    1.55
    Yield
    1.55
     Yield
    1.54
     yield
    1.51
    yield
    1.51
    Activations Density 0.043%

    No Known Activations