© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34677
    Prev
    Next
    INDEX
    Explanations

    match to similar items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ứng
    -1.07
     GreatSchools
    -1.07
    癀
    -1.05
    </sup>
    -1.04
    ')
    -1.02
    ("")){
    -1.01
    桝
    -1.00
     RecyclerView
    -1.00
    ych
    -0.99
    受験
    -0.98
    POSITIVE LOGITS
     other
    1.45
     existing
    1.33
     your
    1.28
     matching
    1.09
     already
    1.08
     predominant
    1.02
     the
    1.01
     on
    0.98
     with
    0.97
     блюдо
    0.97
    Activations Density 0.018%

    No Known Activations