© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11310
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

    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
     of
    -1.12
    なのだ
    -1.07
    らせ
    -1.01
    えました
    -1.00
     segíts
    -0.98
    ってもら
    -0.97
    爰
    -0.96
    ねば
    -0.95
    なのです
    -0.94
    化する
    -0.94
    POSITIVE LOGITS
     perlindungan
    1.08
     kepentingan
    1.04
    Winds
    1.00
    cheidung
    0.99
    是一
    0.98
    hiculo
    0.98
    </em>
    0.97
     gusta
    0.97
     gibi
    0.96
    Trends
    0.95
    Activations Density 0.019%

    No Known Activations