© 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. 13105
    Prev
    Next
    INDEX
    Explanations

    family relationships or allies

    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
     it
    -1.74
     its
    -1.71
     of
    -1.49
     Our
    -1.34
     It
    -1.23
     We
    -1.10
     our
    -1.08
     my
    -1.06
     there
    -1.05
    panou
    -1.02
    POSITIVE LOGITS
     bemer
    1.21
    loggen
    1.20
     runde
    1.18
    parken
    1.15
     eier
    1.13
     bilde
    1.12
     reisen
    1.11
     effekt
    1.10
     choices
    1.10
     herstellen
    1.09
    Activations Density 0.031%

    No Known Activations