© 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. 2912
    Prev
    Next
    INDEX
    Explanations

    explosives or powders

    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
     länge
    -0.74
    厅
    -0.73
    تيجة
    -0.71
    setQuery
    -0.68
    ordre
    -0.68
     συ
    -0.67
     CAMERA
    -0.66
     PCR
    -0.65
     garlic
    -0.65
    PCR
    -0.65
    POSITIVE LOGITS
     powder
    1.62
     powders
    1.37
     Powder
    1.19
    powder
    1.17
    Powder
    1.15
     grains
    0.94
    pulver
    0.90
    stance
    0.82
     yavaş
    0.81
     poudre
    0.80
    Activations Density 0.018%

    No Known Activations