© 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. 75375
    Prev
    Next
    INDEX
    Explanations

    code block 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
     многих
    -1.18
    Likewise
    -1.02
    commonly
    -1.01
    primarily
    -0.96
    Similarly
    -0.95
    generally
    -0.93
     momentan
    -0.92
     reunião
    -0.89
     correspon
    -0.87
    Furthermore
    -0.86
    POSITIVE LOGITS
     its
    1.08
     their
    0.92
    粱
    0.91
     bola
    0.91
     itself
    0.90
     after
    0.90
     Mares
    0.89
     this
    0.89
    ază
    0.88
    casila
    0.88
    Activations Density 0.035%

    No Known Activations