© 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. 10241
    Prev
    Next
    INDEX
    Explanations

    the most important aspect

    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
    recording
    1.38
    Sid
    1.36
    gathered
    1.32
    Kirk
    1.31
    indeki
    1.27
    Interesting
    1.27
    Wind
    1.26
    </code>
    1.26
    Sus
    1.25
    intervals
    1.24
    POSITIVE LOGITS
     guarantee
    1.13
     irrevoc
    1.11
     limit
    1.09
     لاءِ
    1.05
     unconditionally
    1.04
     eternally
    1.03
     바꾸
    1.02
     EVER
    1.00
     ACCEPT
    0.97
     ever
    0.96
    Activations Density 0.442%

    No Known Activations