© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8629
    Prev
    Next
    INDEX
    Explanations

    Nab and SQL keywords

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

    SQL WHERE clauses

    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_40_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
     arrive
    0.38
    //"
    0.38
    "+"|".
    0.38
     DJ
    0.37
     Pope
    0.37
     Pros
    0.36
     ladder
    0.36
     unpopular
    0.36
    ":[{"
    0.34
     mage
    0.34
    POSITIVE LOGITS
     '{}
    0.59
    ='$
    0.53
     '{
    0.52
     '".
    0.49
     '$
    0.48
     '".$
    0.47
     LIKE
    0.46
    ('%
    0.45
     REPLACE
    0.45
     (?,
    0.45
    Activations Density 0.008%

    No Known Activations