© 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. 10-GEMMASCOPE-RES-131K
    7. 105823
    Prev
    Next
    INDEX
    Explanations

    proper nouns or abbreviations

    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_10/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
     élar
    -1.65
     Gummi
    -1.57
     hygge
    -1.51
     religieuses
    -1.48
    ariana
    -1.48
     εἰ
    -1.44
    etero
    -1.44
    舷
    -1.42
     accél
    -1.41
    lijah
    -1.41
    POSITIVE LOGITS
     a
    2.08
     it
    2.05
     on
    1.83
     itself
    1.55
     against
    1.52
     this
    1.47
     four
    1.47
     the
    1.42
    ably
    1.41
     an
    1.41
    Activations Density 0.156%

    No Known Activations