© 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. 84144
    Prev
    Next
    INDEX
    Explanations

    determiner or preposition phrase

    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
     firstly
    -1.24
    そうですが
    -1.19
     MemoryStream
    -1.17
     Firstly
    -1.10
    最初
    -1.06
    とはいえ
    -1.02
    GIUM
    -1.02
    说实话
    -1.02
     =======
    -1.02
     ?>>
    -1.01
    POSITIVE LOGITS
     craindre
    1.45
     thus
    1.32
     also
    1.22
     embarazada
    1.17
    sequently
    1.16
    為に
    1.15
     hence
    1.14
    なのだ
    1.13
     thereby
    1.13
     نیز
    1.13
    Activations Density 0.067%

    No Known Activations