© 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. 22-GEMMASCOPE-RES-131K
    7. 66988
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
    してました
    -0.93
    >(&
    -0.85
    禰
    -0.84
     Glide
    -0.82
    BrowserModule
    -0.81
    Vz
    -0.80
     כוס
    -0.80
    itary
    -0.80
    Źródło
    -0.79
     edildi
    -0.79
    POSITIVE LOGITS
     you
    0.94
    Dichloro
    0.91
    rahat
    0.89
     mécan
    0.88
     sizin
    0.87
    venske
    0.86
    nesi
    0.86
     przen
    0.85
    кові
    0.85
     великолеп
    0.84
    Activations Density 0.003%

    No Known Activations