© 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. 70998
    Prev
    Next
    INDEX
    Explanations

    Introduction Study

    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
    板上
    -1.05
    ()")
    -1.03
    所に
    -1.02
    遑
    -1.02
    所で
    -1.02
    iram
    -1.01
    }*/
    -1.01
    ところに
    -1.00
    の時間
    -0.99
    内心
    -0.98
    POSITIVE LOGITS
    それでは
    1.16
    んじゃ
    1.08
    Vendo
    1.04
     désolés
    1.01
    海鮮
    1.01
    お店
    1.00
    お店の
    1.00
    尔的
    0.99
     FORCES
    0.98
    Здра
    0.96
    Activations Density 0.004%

    No Known Activations