© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13266
    Prev
    Next
    INDEX
    Explanations

    after from the

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

    This neuron detects directional or relational prepositions (e.g. “from,” “to,” “between”) that link one entity or party to another.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     of
    -1.26
    vierten
    -1.08
    mış
    -1.05
    ोंने
    -1.02
     for
    -1.02
    яд
    -1.02
     Campeonato
    -1.02
    kiat
    -0.99
    kien
    -0.98
    ResponseCode
    -0.98
    POSITIVE LOGITS
     its
    1.48
     tentativo
    1.20
     venne
    1.17
     pittore
    1.16
     ordinaria
    1.15
     nessun
    1.14
     fisico
    1.14
     Nå
    1.14
     about
    1.14
    ;</
    1.14
    Activations Density 0.286%

    No Known Activations