© 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. 22-GEMMASCOPE-RES-131K
    7. 93105
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    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
     when
    -1.41
     with
    -1.36
     When
    -1.32
     out
    -1.29
     in
    -1.22
     just
    -1.20
     Some
    -1.20
     if
    -1.20
     as
    -1.17
     since
    -1.14
    POSITIVE LOGITS
     magnific
    1.42
     inconce
    1.20
     intermin
    1.19
     effe
    1.18
     benevol
    1.16
     aktiviert
    1.16
     xan
    1.15
     mediocre
    1.13
    ago
    1.13
     prodig
    1.12
    Activations Density 0.008%

    No Known Activations