© 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. 1398
    Prev
    Next
    INDEX
    Explanations

    of preposition usage

    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
     from
    -2.94
     to
    -2.91
     in
    -2.84
     only
    -2.84
     with
    -2.73
     this
    -2.70
     when
    -2.53
     during
    -2.42
     every
    -2.41
     on
    -2.30
    POSITIVE LOGITS
    镡
    2.31
    -\\
    2.25
    ]")]
    1.93
     AWAY
    1.91
     liksom
    1.88
    ate
    1.87
    (")
    1.86
     étan
    1.86
     nästan
    1.84
    ."],
    1.80
    Activations Density 0.637%

    No Known Activations