© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84116
    Prev
    Next
    INDEX
    Explanations

    prepositions before times or places

    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
    _
    -1.84
     the
    -1.71
     integrados
    -1.69
    >
    -1.51
     bañ
    -1.44
     potranno
    -1.42
    橚
    -1.42
     szybko
    -1.41
    aka
    -1.40
     rutas
    -1.40
    POSITIVE LOGITS
    晚安
    1.59
     by
    1.54
     "..\..\..\
    1.50
     کنند
    1.45
    ()?;
    1.41
     know
    1.40
     in
    1.40
     are
    1.38
     inom
    1.38
    queeze
    1.36
    Activations Density 0.027%

    No Known Activations