© 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. 75581
    Prev
    Next
    INDEX
    Explanations

    wikipedia articles and content

    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
     ,
    -1.44
    </i>
    -1.44
     one
    -1.40
    -
    -1.35
    </h5>
    -1.34
     three
    -1.28
    }
    -1.27
     .
    -1.23
     referrerpolicy
    -1.23
     but
    -1.23
    POSITIVE LOGITS
     também
    1.92
     también
    1.58
     også
    1.50
     також
    1.49
    OREM
    1.44
     tambien
    1.41
    অ
    1.40
     consacré
    1.39
     также
    1.37
     brilho
    1.36
    Activations Density 0.039%

    No Known Activations