© 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. 36196
    Prev
    Next
    INDEX
    Explanations

    connecting clauses with and

    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
     ſou
    -3.06
    🫃
    -2.84
     mikrofon
    -2.84
     rése
    -2.72
    𓁹
    -2.66
     kabát
    -2.61
    archiwizowane
    -2.59
    熜
    -2.59
     balkon
    -2.58
     dekol
    -2.58
    POSITIVE LOGITS
     it
    4.31
     then
    3.77
     when
    3.45
     although
    3.39
     they
    3.31
     since
    3.16
     if
    3.13
     for
    3.13
     after
    3.05
     there
    2.95
    Activations Density 0.162%

    No Known Activations