© 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. 34-GEMMASCOPE-RES-131K
    7. 64983
    Prev
    Next
    INDEX
    Explanations

    mud and mudslinging

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

    The neuron is keyed to words describing soft or unstable ground surfaces (e.g. mud, sand, turf).

    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
     nécessaire
    -0.78
    сында
    -0.77
     tehdä
    -0.76
    諡
    -0.73
     hermé
    -0.73
     კ
    -0.73
     Roskov
    -0.73
    idences
    -0.72
     reef
    -0.72
     reefs
    -0.71
    POSITIVE LOGITS
     mud
    3.58
    mud
    2.98
    Mud
    2.91
     muddy
    2.83
     Mud
    2.75
    泥
    2.38
    MUD
    2.30
     MUD
    2.28
     泥
    2.13
     гря
    2.11
    Activations Density 0.025%

    No Known Activations