© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84165
    Prev
    Next
    INDEX
    Explanations

    headings introductory phrases

    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
     in
    -1.21
     by
    -1.20
     at
    -1.16
     if
    -1.14
     typically
    -1.12
     what
    -1.09
     on
    -1.08
     і
    -1.04
     or
    -1.03
     enhancing
    -1.00
    POSITIVE LOGITS
     alcune
    1.09
    ></
    1.02
     ridiculously
    0.99
     herunterladen
    0.99
    ;</
    0.99
     erhi
    0.99
     certamente
    0.98
    ragma
    0.98
     ständig
    0.98
     ""}
    0.96
    Activations Density 0.000%

    No Known Activations