© 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. 110857
    Prev
    Next
    INDEX
    Explanations

    al and Arabic proper nouns

    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
     if
    -2.86
    0
    -2.72
     -
    -2.66
     when
    -2.64
     sizeable
    -2.19
     at
    -2.16
     with
    -2.16
     for
    -2.09
     facilitating
    -2.06
    4
    -2.03
    POSITIVE LOGITS
     amazingly
    2.70
     wonderfully
    2.66
     deliciously
    2.48
     delightfully
    2.48
     exceptionally
    2.48
     famed
    2.45
     unbelievably
    2.44
     nowy
    2.42
     extremely
    2.42
     the
    2.42
    Activations Density 0.000%

    No Known Activations