© 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. 10-GEMMASCOPE-RES-131K
    7. 104557
    Prev
    Next
    INDEX
    Explanations

    God's actions and possessions

    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_10/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
     Charakter
    -1.42
    𝕭
    -1.38
    "]
    -1.37
    gées
    -1.33
    各样的
    -1.30
    媜
    -1.30
    ᥬ
    -1.30
     wła
    -1.27
    isierte
    -1.27
    kurtka
    -1.26
    POSITIVE LOGITS
     новой
    1.48
     "
    1.45
    新的
    1.43
     dasselbe
    1.32
     隆
    1.32
    新しい
    1.30
    -
    1.29
     自分
    1.28
     they
    1.26
     again
    1.26
    Activations Density 0.009%

    No Known Activations