© 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. 108060
    Prev
    Next
    INDEX
    Explanations

    dropped or dropping something

    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
     Ско
    -0.73
    debounce
    -0.66
    şik
    -0.66
    TRAVEL
    -0.65
    IALOG
    -0.64
     Dt
    -0.64
    mojo
    -0.63
     percol
    -0.63
     déc
    -0.63
     reis
    -0.62
    POSITIVE LOGITS
     dropped
    6.28
     dropping
    5.72
     drop
    5.53
     drops
    4.94
    Drop
    4.91
    drop
    4.88
    dropped
    4.88
     Drop
    4.84
    dropping
    4.66
    Dropped
    4.66
    Activations Density 0.041%

    No Known Activations