© 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. 130729
    Prev
    Next
    INDEX
    Explanations

    nostalgia for past decades

    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
     Orrell
    -1.20
     gevallen
    -1.16
     októ
    -1.16
    💴
    -1.15
     Atenas
    -1.14
    珐
    -1.13
     kapac
    -1.13
     kontaktu
    -1.13
    σμο
    -1.10
    وردار
    -1.09
    POSITIVE LOGITS
     klarer
    1.19
     era
    1.16
     bakom
    1.03
     both
    1.02
    QUÉ
    1.02
     outskirts
    1.02
     paraphernalia
    1.01
     style
    1.00
     głównie
    0.94
     An
    0.93
    Activations Density 0.019%

    No Known Activations