© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33566
    Prev
    Next
    INDEX
    Explanations

    enum labels and programming keywords

    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
     the
    -1.26
    唐揚げ
    -1.13
     SIX
    -1.09
    Touchable
    -1.08
     sỉ
    -1.06
     Secrétaire
    -1.05
     草莓
    -1.03
     najdete
    -0.99
     it
    -0.98
    harusnya
    -0.98
    POSITIVE LOGITS
    ↵↵↵
    1.21
     other
    1.16
    ↵↵↵↵↵↵↵↵
    1.07
    ↵↵↵↵
    1.06
    ↵↵↵↵↵↵↵↵↵↵
    1.05
    "){
    1.05
     or
    1.05
     မ
    1.05
     hacer
    1.02
    ↵↵↵↵↵↵
    0.97
    Activations Density 0.018%

    No Known Activations