© 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. 84348
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or complements

    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
    RTLE
    -1.16
     scurt
    -1.03
    Sonntag
    -1.02
    Schön
    -1.02
     岁
    -1.02
    がありますが
    -1.00
     unele
    -1.00
    quing
    -0.99
    けどね
    -0.99
     Hijo
    -0.99
    POSITIVE LOGITS
     and
    1.38
     a
    1.24
     or
    1.17
     to
    1.16
    .”
    1.10
    <!--
    1.06
     The
    1.02
    €“
    1.00
    ➞
    0.99
    ？
    0.98
    Activations Density 0.058%

    No Known Activations