© 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. 36507
    Prev
    Next
    INDEX
    Explanations

    clauses after commas

    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
     gesuchten
    -1.28
    albeit
    -1.23
    醗
    -1.18
     سواء
    -1.10
    篌
    -1.09
    perhaps
    -1.05
     decidi
    -1.05
    ㈡
    -1.04
    thats
    -1.03
    そして
    -1.02
    POSITIVE LOGITS
     which
    1.82
    եւ
    1.19
     який
    1.13
    ilarang
    1.13
     where
    1.10
     and
    1.10
     moverse
    1.08
    綽
    1.06
     яка
    1.03
     with
    1.01
    Activations Density 0.104%

    No Known Activations