© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14675
    Prev
    Next
    INDEX
    Explanations

    class names related to streams and utilities

    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
    ществует
    -1.27
     همچنین
    -1.20
    任何
    -1.16
    様な
    -1.13
     любых
    -1.12
     leão
    -1.06
     continuó
    -1.05
     Unterschied
    -1.05
     особенно
    -1.04
     like
    -1.02
    POSITIVE LOGITS
     it
    1.06
    するの
    1.05
     delar
    1.02
    はかなり
    1.02
     traje
    0.99
     cromo
    0.98
     didn
    0.98
     _('
    0.97
    ～」
    0.96
     låg
    0.96
    Activations Density 0.015%

    No Known Activations