© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10677
    Prev
    Next
    INDEX
    Explanations

    stars exhibiting properties or formations

    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
     situato
    -1.76
    
    -1.57
    ]{\
    -1.56
    phère
    -1.55
     peliculas
    -1.55
     avocado
    -1.52
    ்கு
    -1.48
    稣
    -1.48
    ogenicity
    -1.45
    pered
    -1.45
    POSITIVE LOGITS
    </h1>
    1.94
     When
    1.52
    -
    1.42
    </h2>
    1.38
     Any
    1.36
     With
    1.34
     While
    1.32
     There
    1.31
    </i>
    1.28
     Before
    1.27
    Activations Density 0.027%

    No Known Activations