© 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. 10160
    Prev
    Next
    INDEX
    Explanations

    concept of sin

    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
    al
    -2.25
     \%}$
    -2.09
    価格は
    -2.08
    就想
    -2.05
    感じで
    -2.05
    サイズは
    -2.02
    問題は
    -2.02
    uttgart
    -2.00
    usitis
    -1.99
    ーズン
    -1.95
    POSITIVE LOGITS
    翆
    2.38
     Desde
    2.06
    ).
    2.03
     Aunque
    1.96
     entweder
    1.81
    HAHAHAHA
    1.77
    валі
    1.77
     グラフ
    1.76
     inocente
    1.76
    梵
    1.75
    Activations Density 0.005%

    No Known Activations