© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13334
    Prev
    Next
    INDEX
    Explanations

    eliminate this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     strawberries
    0.85
     Miracle
    0.83
     wrongly
    0.81
     peas
    0.81
     pepper
    0.80
     cucumber
    0.80
    枇
    0.80
     ginger
    0.79
    peas
    0.78
     asparagus
    0.78
    POSITIVE LOGITS
    猖
    1.18
     मुख्यालय
    1.13
     desafío
    1.11
    ्हान
    1.05
    掌控
    1.03
     Sentencing
    1.02
     desafios
    1.01
     डीजल
    0.97
     Hd
    0.96
     சமூக
    0.96
    Activations Density 0.245%

    No Known Activations