© 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. 12483
    Prev
    Next
    INDEX
    Explanations

    numbers of family members

    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
     then
    -1.23
     ܙ
    -0.94
     jusque
    -0.92
    Ⓦ
    -0.91
     σελ
    -0.90
    한다
    -0.89
     erzeugt
    -0.89
    ピアノ
    -0.88
     largely
    -0.88
     proberen
    -0.88
    POSITIVE LOGITS
     with
    1.09
     masih
    1.07
    Two
    1.04
    ．．．
    1.01
     ecol
    1.00
    Three
    0.98
    ･･
    0.97
    There
    0.96
     apare
    0.96
    With
    0.94
    Activations Density 0.001%

    No Known Activations