© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111425
    Prev
    Next
    INDEX
    Explanations

    earth, excavation, materials

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

    The neuron activates on terminology related to earth-moving or excavation equipment and operations.

    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
    !");
    
    -1.35
     Fête
    -1.33
     vás
    -1.29
    ❔
    -1.28
     ENGLAND
    -1.27
     CIVIL
    -1.27
     MINISTER
    -1.27
     pierdas
    -1.25
     villes
    -1.24
    νει
    -1.24
    POSITIVE LOGITS
     to
    1.88
     about
    1.53
     or
    1.45
     with
    1.41
     the
    1.37
     for
    1.30
    ;
    1.30
     There
    1.27
     only
    1.24
    ".
    1.21
    Activations Density 0.020%

    No Known Activations