© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6714
    Prev
    Next
    INDEX
    Explanations

    whales and breaching

    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_22_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
     palud
    1.36
     snails
    1.21
    Insect
    1.17
     Lizard
    1.16
     insects
    1.13
     worms
    1.12
     Insects
    1.10
    蛙
    1.09
     pheasant
    1.07
    тье
    1.05
    POSITIVE LOGITS
     spout
    1.10
     whale
    1.09
     Cet
    1.07
     odont
    1.04
     Orc
    1.04
     hump
    1.03
     cet
    1.03
    イル
    1.03
     whales
    1.02
     pod
    1.02
    Activations Density 0.173%

    No Known Activations