© 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. 32451
    Prev
    Next
    INDEX
    Explanations

    explosive charge materials and munitions

    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
    Sunday
    -0.77
     Три
    -0.74
     bety
    -0.72
    线下
    -0.72
     invasion
    -0.72
    ckner
    -0.72
     света
    -0.71
    пру
    -0.71
    ursday
    -0.71
     Doug
    -0.70
    POSITIVE LOGITS
     charges
    2.73
     charge
    2.28
     Charges
    2.03
    Charges
    1.96
    charges
    1.89
     explosives
    1.77
     explosive
    1.67
    charge
    1.62
     Charge
    1.55
    Charge
    1.54
    Activations Density 0.045%

    No Known Activations