© 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. 9631
    Prev
    Next
    INDEX
    Explanations

    nouns followed by prepositions

    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
     améliorer
    -1.27
    给自己
    -1.26
    硨
    -1.22
    abinieri
    -1.18
    읭
    -1.17
     zyn
    -1.16
     Laine
    -1.16
    ՚
    -1.16
     nmd
    -1.14
    の中から
    -1.13
    POSITIVE LOGITS
     from
    1.84
     in
    1.82
     at
    1.76
     of
    1.75
     with
    1.66
     through
    1.52
     via
    1.35
     by
    1.34
     for
    1.20
     or
    1.17
    Activations Density 0.035%

    No Known Activations