© 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. 343
    Prev
    Next
    INDEX
    Explanations

    prefix or start of words

    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
     so
    -1.33
     you
    -1.25
     
    -1.15
     even
    -1.09
     one
    -1.09
     فقد
    -1.08
    even
    -1.08
     by
    -1.08
     it
    -1.05
     we
    -1.02
    POSITIVE LOGITS
    ToMany
    1.13
    Ŕ
    1.10
    îné
    1.09
     سیب
    1.09
    tiembre
    1.07
    antism
    1.05
    printStats
    1.05
    ARROLLO
    1.03
    ìn
    1.02
    /}
    1.02
    Activations Density 0.228%

    No Known Activations