© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32994
    Prev
    Next
    INDEX
    Explanations

    titles 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
     نداشته
    -1.28
    の関係
    -1.27
     kutumia
    -1.25
    交渉
    -1.24
     πρ
    -1.23
    ΰ
    -1.23
     sarili
    -1.22
     uchiha
    -1.21
    ּוֹ
    -1.21
     Frankfurt
    -1.21
    POSITIVE LOGITS
    Ekster
    1.35
     сыром
    1.27
     блюдо
    1.26
    Πηγ
    1.24
     tollen
    1.20
     rozs
    1.18
     leader
    1.14
    ׇ
    1.13
     вместо
    1.13
    瘜
    1.13
    Activations Density 0.001%

    No Known Activations