© 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. 130719
    Prev
    Next
    INDEX
    Explanations

    code identifiers ending with 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
     of
    -1.47
     for
    -1.45
     so
    -1.07
     no
    -1.06
     other
    -1.04
     to
    -0.98
    op
    -0.93
    D
    -0.93
     E
    -0.93
     da
    -0.92
    POSITIVE LOGITS
     resultaten
    1.15
    labili
    1.06
    larak
    1.05
    CELONA
    1.05
     sorprender
    1.02
    Italien
    1.02
    屨
    1.01
     telefonu
    0.98
     Probl
    0.98
    といいます
    0.96
    Activations Density 0.023%

    No Known Activations