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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15853
    Prev
    Next
    INDEX
    Explanations

    code structure declarations

    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
    Zdroje
    -1.09
    
    -1.05
    عالی
    -1.03
     \#:
    -1.02
    ㎎
    -1.01
     centavos
    -0.98
     giudice
    -0.98
    بدون
    -0.98
     أيض
    -0.97
    ⎧
    -0.97
    POSITIVE LOGITS
    ?
    1.16
     autre
    1.08
     incluidas
    1.08
    entamiento
    1.05
    ラウンド
    1.05
    就行了
    1.04
    时机
    1.03
    ありません
    1.02
    就可以了
    1.02
     Фото
    1.02
    Activations Density 0.034%

    No Known Activations