© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69128
    Prev
    Next
    INDEX
    Explanations

    homework help online Explained

    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
    </h5>
    -1.24
    "]
    -1.23
    一旁
    -1.22
     ")
    -1.22
    obatan
    -1.18
     a
    -1.18
    』『
    -1.18
    ي
    -1.16
    "]').
    -1.15
    </h4>
    -1.14
    POSITIVE LOGITS
    Océ
    1.41
    
    1.36
     vertellen
    1.35
    很赞
    1.32
     proberen
    1.32
    août
    1.32
     deberían
    1.31
     яке
    1.28
     leveren
    1.27
     можуть
    1.25
    Activations Density 0.053%

    No Known Activations