© 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. 2708
    Prev
    Next
    INDEX
    Explanations

    adjective noun phrase

    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
    ↵↵
    1.55
     However
    1.33
     simply
    1.23
     on
    1.22
     not
    1.20
     el
    1.16
     en
    1.15
    However
    1.14
     however
    1.13
     being
    1.13
    POSITIVE LOGITS
    愤怒
    2.25
    𒆪
    2.21
     создании
    2.19
    𒉈
    2.18
    𒀝
    2.18
    𒊑
    2.17
     обновления
    2.16
     убий
    2.14
    𒌨
    2.14
     миллионов
    2.13
    Activations Density 0.494%

    No Known Activations