© 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. 60699
    Prev
    Next
    INDEX
    Explanations

    heavy-duty or resistant materials

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

    The neuron flags engineering specification terms and capacity/rating words—especially units and metrics like ampacity, voltage, pressure, strength, and similar technical ratings.

    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
    vermectin
    -1.41
    arrived
    -1.33
    acknowled
    -1.32
    
    -1.31
    ocide
    -1.28
    acknowledge
    -1.27
     sisält
    -1.26
    entered
    -1.26
    arrive
    -1.25
     itong
    -1.25
    POSITIVE LOGITS
     также
    1.19
    であれば
    1.16
    頂きました
    1.16
    P
    1.12
     with
    1.11
     of
    1.11
     centuries
    1.09
     stemming
    1.07
    これらの
    1.07
    います
    1.07
    Activations Density 0.074%

    No Known Activations