© 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. 10-GEMMASCOPE-RES-131K
    7. 9319
    Prev
    Next
    INDEX
    Explanations

    to be or other verbs

    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_10/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
     этих
    -2.31
     российских
    -2.14
    ("
    -2.09
     tämä
    -2.08
    駡
    -2.06
     utilisent
    -2.05
    wendige
    -2.00
    乆
    -2.00
     них
    -1.96
    t
    -1.93
    POSITIVE LOGITS
     as
    2.08
     to
    1.98
     because
    1.92
     tetapi
    1.91
     and
    1.90
     what
    1.81
     an
    1.79
     have
    1.78
     by
    1.71
     want
    1.70
    Activations Density 0.010%

    No Known Activations