© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 269
    Prev
    Next
    INDEX
    Explanations

    my or our possession

    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
     différents
    -1.48
    various
    -1.41
     pittores
    -1.38
     mauva
    -1.23
     différentes
    -1.23
     pernic
    -1.23
    different
    -1.20
    besos
    -1.19
    both
    -1.18
     olika
    -1.17
    POSITIVE LOGITS
     that
    1.89
     or
    1.62
     which
    1.52
     Even
    1.37
     could
    1.34
     at
    1.33
     estas
    1.30
     When
    1.23
     During
    1.22
     on
    1.20
    Activations Density 0.085%

    No Known Activations