© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10204
    Prev
    Next
    INDEX
    Explanations

    labeling values with colon

    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_7_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
    ÍN
    1.49
    ása
    1.48
    ClkInitStruct
    1.47
    ások
    1.46
    IRQHandler
    1.43
    Ỳ
    1.42
     velmi
    1.41
    ኔ
    1.41
     tł
    1.39
     ngành
    1.38
    POSITIVE LOGITS
     tain
    1.38
     crest
    1.31
    atac
    1.24
     adrift
    1.22
     smack
    1.21
     unters
    1.21
     absorbing
    1.20
     overrun
    1.18
     strands
    1.17
     fe
    1.17
    Activations Density 0.008%

    No Known Activations