© 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. 84368
    Prev
    Next
    INDEX
    Explanations

    groups collected together

    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
    3
    -1.12
     your
    -1.08
     beiden
    -1.04
     встречи
    -1.04
     –
    -1.03
     recepción
    -1.01
     Begegn
    -1.00
    …
    -0.98
    your
    -0.98
    self
    -0.96
    POSITIVE LOGITS
     collective
    1.71
     group
    1.48
     unanim
    1.39
    semble
    1.37
     unison
    1.33
     assembled
    1.32
    collective
    1.32
     their
    1.32
    กลุ่ม
    1.30
     groups
    1.27
    Activations Density 0.065%

    No Known Activations