© 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. 34-GEMMASCOPE-RES-131K
    7. 118292
    Prev
    Next
    INDEX
    Explanations

    contractions ending in it, you, they

    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_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
    styleable
    -0.80
     שנים
    -0.78
     Juniper
    -0.76
     свою
    -0.75
     its
    -0.75
    cott
    -0.75
    Calle
    -0.73
     Calle
    -0.72
    はその
    -0.72
    ziosi
    -0.72
    POSITIVE LOGITS
     afspraak
    0.81
    ouldering
    0.80
    hoea
    0.79
    隋
    0.78
     they
    0.78
     која
    0.76
    ﺖ
    0.76
     extraordinary
    0.76
    ztes
    0.75
    ITUTION
    0.74
    Activations Density 0.007%

    No Known Activations