© 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. 33380
    Prev
    Next
    INDEX
    Explanations

    BBC, NHK, and media outlets

    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
     Schle
    -0.79
    osen
    -0.73
    rila
    -0.71
     Publishers
    -0.71
    доль
    -0.69
    ئے
    -0.69
     จำ
    -0.69
     getLayout
    -0.69
     prze
    -0.68
    ⥤
    -0.68
    POSITIVE LOGITS
     BBC
    2.39
    BBC
    2.16
    bbc
    1.91
     bbc
    1.84
     NHK
    1.05
     Auntie
    0.90
    NHK
    0.88
     Radio
    0.82
     SSB
    0.81
     Рус
    0.79
    Activations Density 0.045%

    No Known Activations