© 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. 22-GEMMASCOPE-RES-131K
    4. 98478
    Prev
    Next
    INDEX
    Explanations

    forwarded messages or git diffs

    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_22/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
     this
    -1.76
     when
    -1.27
     apartamento
    -1.27
     if
    -1.20
     every
    -1.18
    ==(
    -1.16
     their
    -1.14
    ❣
    -1.11
     União
    -1.11
     África
    -1.10
    POSITIVE LOGITS
     myriad
    1.25
     revamped
    1.21
    particularly
    1.20
    mainly
    1.20
     opulent
    1.20
    o
    1.20
    établissement
    1.17
     gigantic
    1.17
     flamboyant
    1.17
     marvelous
    1.16
    Activations Density 0.001%

    No Known Activations