© 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. 10-GEMMASCOPE-RES-131K
    7. 59951
    Prev
    Next
    INDEX
    Explanations

    best superlative adjectives

    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_10/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
     Mereka
    -1.37
     Khusus
    -1.25
     ОБ
    -1.21
    smallskip
    -1.06
     or
    -1.05
    又不
    -1.04
    Lua
    -1.04
    Caracter
    -1.03
    BrowserModule
    -1.02
     nyingi
    -1.02
    POSITIVE LOGITS
     need
    1.29
     totul
    1.20
     forskellige
    1.16
     closer
    1.10
     already
    1.09
    不同
    1.09
     precisam
    1.05
    用
    1.02
     eene
    1.01
     chaises
    1.01
    Activations Density 0.113%

    No Known Activations