© 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. 34-GEMMASCOPE-RES-131K
    7. 70093
    Prev
    Next
    INDEX
    Explanations

    code comments and special characters

    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_34/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
    આ
    -1.15
     colgante
    -1.09
    ЕНЬ
    -1.06
     sanoo
    -1.03
     peruan
    -1.02
     rése
    -1.02
     ;
    -1.02
     victoires
    -1.01
     parfü
    -1.01
    '];
    -1.01
    POSITIVE LOGITS
     now
    1.67
     prepare
    1.34
    elif
    1.34
     construct
    1.24
     again
    1.23
     here
    1.22
     getting
    1.20
     choose
    1.20
     preparing
    1.19
     for
    1.16
    Activations Density 0.005%

    No Known Activations