© 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. 521
    Prev
    Next
    INDEX
    Explanations

    a confirmation followed by punctuation

    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
     to
    -1.49
     with
    -1.06
     while
    -1.03
     for
    -0.98
     and
    -0.95
     мульт
    -0.93
     or
    -0.91
     such
    -0.88
     as
    -0.87
     zondag
    -0.86
    POSITIVE LOGITS
     it
    1.34
    That
    1.15
     навіть
    1.02
    pecially
    0.95
    ływ
    0.94
    ⼀
    0.94
     เร
    0.94
    りました
    0.93
     нём
    0.93
     даже
    0.91
    Activations Density 0.023%

    No Known Activations