© 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. 66538
    Prev
    Next
    INDEX
    Explanations

    section numbering and references

    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
    faro
    -1.08
    さぁ
    -1.05
    にほんブログ村
    -1.04
     takich
    -1.01
    今週
    -1.01
    auces
    -0.99
    あー
    -0.99
    ïdes
    -0.98
    昨日の
    -0.98
    ysy
    -0.98
    POSITIVE LOGITS
     (
    1.34
    1
    1.14
    2
    1.07
    車は
    1.02
    ガキ
    1.01
    <bos>
    1.00
    ですが
    0.97
     Nagasaki
    0.95
     ноутбу
    0.95
    3
    0.94
    Activations Density 0.012%

    No Known Activations