© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 49157
    Prev
    Next
    INDEX
    Explanations

    preposition followed by modifier

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on very short common function words—especially the two-letter prepositions “in,” “to,” and “at.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    }$.
    -1.66
    傒
    -1.42
    そのため
    -1.38
     }}$.
    -1.38
    )}$.
    -1.37
     imedi
    -1.34
    これは
    -1.34
    logrus
    -1.30
    最近は
    -1.28
     pernic
    -1.27
    POSITIVE LOGITS
     {},
    1.56
    !,
    1.52
    ?,
    1.38
     presumably
    1.33
    *,
    1.27
     from
    1.26
     perhaps
    1.25
     [],
    1.23
     "",
    1.21
     still
    1.19
    Activations Density 0.107%

    No Known Activations