© 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. 12945
    Prev
    Next
    INDEX
    Explanations

    URL placeholders like {VENUE_ID}

    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
    が
    -1.14
    も
    -1.09
    te
    -1.05
    を
    -1.03
     proveniente
    -1.02
    o
    -1.01
    chapper
    -1.00
     ei
    -0.99
    と
    -0.99
    often
    -0.99
    POSITIVE LOGITS
     their
    1.48
    iqué
    1.37
    zku
    1.29
     its
    1.29
    Zunanje
    1.21
     gustar
    1.16
     with
    1.13
    もうすぐ
    1.13
    ัณฑ์
    1.13
    ၀
    1.09
    Activations Density 0.005%

    No Known Activations