© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39447
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency and manner

    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
     trajets
    -1.36
     aperçu
    -1.34
    饸
    -1.30
     クラフト
    -1.27
     séjours
    -1.23
     botines
    -1.23
    jść
    -1.20
     ſur
    -1.18
     sentiers
    -1.17
    ㈲
    -1.16
    POSITIVE LOGITS
    ),
    1.34
     frantic
    1.32
     epitom
    1.31
     any
    1.30
     before
    1.29
     проє
    1.21
    Very
    1.20
     stellar
    1.19
     Very
    1.18
    !!!!!
    1.17
    Activations Density 0.043%

    No Known Activations