© 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. 36357
    Prev
    Next
    INDEX
    Explanations

    prepositions and short function 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
     which
    -2.05
     that
    -1.59
     Although
    -1.52
     by
    -1.30
    场比赛
    -1.30
     There
    -1.27
     oraz
    -1.25
     should
    -1.23
     )}$
    -1.23
     Despite
    -1.20
    POSITIVE LOGITS
     gebraucht
    1.21
     apprécier
    1.19
     feront
    1.16
    買って
    1.13
     funguje
    1.13
     ſen
    1.13
     naudo
    1.12
     télécharge
    1.08
    inawa
    1.08
     Prehistoric
    1.07
    Activations Density 0.120%

    No Known Activations