© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73014
    Prev
    Next
    INDEX
    Explanations

    DC Comics characters and universe

    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
     blieb
    -1.41
    瑧
    -1.41
     like
    -1.39
    on
    -1.38
    つる
    -1.36
    *
    -1.34
     mencion
    -1.34
     how
    -1.33
     международ
    -1.31
     you
    -1.30
    POSITIVE LOGITS
     frattempo
    1.52
    ꦥ
    1.38
     tempt
    1.34
    Ты
    1.33
    irmingham
    1.32
     voren
    1.30
     اینکه
    1.28
     BEAUT
    1.27
     LEGEND
    1.27
     concorso
    1.27
    Activations Density 0.011%

    No Known Activations