© 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. 68935
    Prev
    Next
    INDEX
    Explanations

    relationships and social dynamics

    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
     samtidigt
    -1.31
    alternative
    -1.12
    nitz
    -1.11
    还需要
    -1.11
    ンドル
    -1.09
    ↵↵
    -1.08
     diec
    -1.05
    -1.05
     erzeugen
    -1.05
    icago
    -1.04
    POSITIVE LOGITS
     piccola
    1.16
     competition
    1.08
     ganado
    1.07
    dekor
    1.05
    ånga
    1.05
     older
    1.05
     interaction
    1.04
     апель
    1.04
     they
    1.03
     игра
    1.03
    Activations Density 0.012%
    No Known Activations