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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66321
    Prev
    Next
    INDEX
    Explanations

    African languages and regions

    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
     each
    -1.22
     it
    -1.21
    着一个
    -1.10
     which
    -1.08
    了几
    -1.03
     ingrediente
    -1.02
    LoadScene
    -1.02
     masculina
    -1.00
     often
    -0.99
    我这
    -0.99
    POSITIVE LOGITS
     dimentic
    1.20
     betreffende
    1.16
     ricev
    1.15
     preghi
    1.13
     ہم
    1.09
    rrrrrr
    1.08
    uuuuu
    1.07
    breakers
    1.03
    xun
    1.03
     ameryka
    1.02
    Activations Density 0.005%

    No Known Activations