© 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. 28621
    Prev
    Next
    INDEX
    Explanations

    discord bot

    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
     our
    -1.45
     vienas
    -1.26
     such
    -1.20
    ❤️❤️❤️
    -1.17
     viena
    -1.16
     certainly
    -1.16
     government
    -1.14
    Regarding
    -1.13
     with
    -1.13
     those
    -1.13
    POSITIVE LOGITS
    formen
    1.30
    dropIfExists
    1.20
     către
    1.13
    namientos
    1.09
     alcalde
    1.09
    ᚄ
    1.08
    蛀
    1.07
     hice
    1.05
    baren
    1.05
    tas
    1.05
    Activations Density 0.016%

    No Known Activations