© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12178
    Prev
    Next
    INDEX
    Explanations

    waste disposal dumpster

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

    sequence, numbers, charge, breach, kindling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    0.57
    corto
    0.48
    their
    0.47
    possessed
    0.47
     इज़
    0.45
    o
    0.45
    ri
    0.43
    rb
    0.43
    cheng
    0.43
    south
    0.43
    POSITIVE LOGITS
     chimney
    0.57
    鸬
    0.53
     bungee
    0.50
     nib
    0.49
     stille
    0.49
     kopi
    0.48
     contrace
    0.48
     hibernate
    0.48
     excision
    0.48
     hydros
    0.48
    Activations Density 0.005%

    No Known Activations