© 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. 12553
    Prev
    Next
    INDEX
    Explanations

    court of appeals districts

    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
     from
    -1.70
     very
    -1.38
    oczes
    -1.25
     Вода
    -1.22
     perhaps
    -1.17
     all
    -1.16
     told
    -1.16
     some
    -1.16
     their
    -1.16
    !
    -1.15
    POSITIVE LOGITS
    ַּ
    1.59
    áles
    1.56
    ּוֹ
    1.55
    flasche
    1.51
     وزار
    1.48
    ִּ
    1.45
     AssemblyCulture
    1.43
     grotte
    1.41
    Ṇ
    1.40
    群众
    1.37
    Activations Density 0.003%

    No Known Activations