© 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. 109562
    Prev
    Next
    INDEX
    Explanations

    reporting statements by leaders

    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
     and
    -1.55
     tulis
    -1.30
     santai
    -1.04
    pakan
    -1.04
    rajz
    -1.03
     miliki
    -1.03
     historiador
    -1.02
    kontak
    -1.02
     protokol
    -1.00
    dür
    -0.99
    POSITIVE LOGITS
     said
    2.25
     also
    2.20
     further
    1.97
     however
    1.80
     then
    1.52
     added
    1.47
     therefore
    1.44
     furthermore
    1.40
     inoltre
    1.35
     explained
    1.29
    Activations Density 0.007%

    No Known Activations