© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76518
    Prev
    Next
    INDEX
    Explanations

    firearm magazines

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Axes
    -0.84
    avu
    -0.76
     morn
    -0.75
    هاد
    -0.73
    utch
    -0.73
    curkan
    -0.72
    SqlClient
    -0.71
    déric
    -0.70
    OGND
    -0.69
    חות
    -0.68
    POSITIVE LOGITS
     magazine
    2.17
     magazines
    2.03
     Magazine
    1.67
    magazine
    1.55
     capacity
    1.53
     Magazines
    1.45
    capacity
    1.44
    Magazine
    1.42
     MAGAZINE
    1.40
    magaz
    1.35
    Activations Density 0.014%

    No Known Activations