© 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. 10481
    Prev
    Next
    INDEX
    Explanations

    software optimization and experience

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tained
    2.42
    দি
    2.35
    #>
    2.25
     piace
    2.22
     வி
    2.21
     ch
    2.18
    ə
    2.14
    bauer
    2.11
    료
    2.10
    моби
    2.10
    POSITIVE LOGITS
    Incoming
    3.48
    itudinal
    3.28
    chtenstein
    3.19
     लकार
    3.14
    jgl
    3.14
    ೃಷ್ಣ
    3.13
    enbach
    3.12
    鏁
    3.10
    esor
    3.09
     TRANSPORTURI
    3.01
    Activations Density 0.497%

    No Known Activations