© 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. 34-GEMMASCOPE-RES-131K
    7. 109094
    Prev
    Next
    INDEX
    Explanations

    in retrospect

    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_34/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
    ued
    -0.88
    jonen
    -0.87
     ожида
    -0.85
     még
    -0.84
     citer
    -0.81
     besti
    -0.81
     ordre
    -0.80
     Dictionnaire
    -0.79
    inner
    -0.78
     위한
    -0.78
    POSITIVE LOGITS
     hindsight
    6.09
     retrospect
    5.34
     retrospec
    3.73
     retrospective
    3.31
    Hind
    3.13
    retro
    3.06
    hind
    2.98
    Retro
    2.97
     Hind
    2.83
     retro
    2.81
    Activations Density 0.031%

    No Known Activations