© 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. 22-GEMMASCOPE-RES-131K
    7. 576
    Prev
    Next
    INDEX
    Explanations

    in the

    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
     you
    -1.55
     we
    -1.49
     our
    -1.45
     الجلد
    -1.20
     where
    -1.20
     дуже
    -1.13
     what
    -1.06
     my
    -1.05
     Национальный
    -1.05
    Ŭ
    -1.05
    POSITIVE LOGITS
     said
    1.40
     earlier
    1.32
     другой
    1.29
    ᾿
    1.27
     last
    1.27
    ὲ
    1.21
     rispond
    1.20
     Tuesday
    1.20
     Wednesday
    1.14
    rée
    1.12
    Activations Density 0.024%

    No Known Activations