© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176041
    Prev
    Next
    INDEX
    Explanations

    democratic accountability

    np_acts-logits-general · gemini-2.5-flash-lite

    taking or relying on instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ,
    0.51
    per
    0.48
     iconic
    0.48
    Q
    0.46
    high
    0.46
    mittedly
    0.45
     myriad
    0.45
      
    0.45
    umerable
    0.45
    </code>
    0.44
    POSITIVE LOGITS
     выну
    0.50
    霰
    0.48
     préférable
    0.47
     কাকে
    0.45
     উইকেট
    0.45
     прозра
    0.45
     کھانا
    0.45
     dépens
    0.45
     nécessaire
    0.44
     Jaipur
    0.44
    Activations Density 0.002%

    No Known Activations