© 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. 36319
    Prev
    Next
    INDEX
    Explanations

    reposting, reprinting, rereading

    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
    yttö
    -0.89
    ǿ
    -0.82
     시작
    -0.80
     ersten
    -0.77
    yttä
    -0.74
    sourceforge
    -0.74
     modernize
    -0.73
    hastly
    -0.73
     both
    -0.72
     Replacement
    -0.72
    POSITIVE LOGITS
     повтор
    1.40
     nochmal
    1.27
     previously
    1.27
     revisited
    1.23
    previously
    1.20
     rerun
    1.20
     revisit
    1.16
     reread
    1.13
    Previously
    1.10
     previous
    1.09
    Activations Density 0.148%

    No Known Activations