© 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. 69464
    Prev
    Next
    INDEX
    Explanations

    key feature descriptors

    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
    }
    -2.31
    </i>
    -1.98
     básicamente
    -1.91
     frecuentemente
    -1.91
     creada
    -1.81
     necesariamente
    -1.79
     ciertos
    -1.77
     estrictamente
    -1.73
     Could
    -1.69
     flagrant
    -1.69
    POSITIVE LOGITS
     strane
    2.47
     ihre
    2.09
     garganta
    2.08
    宬
    2.02
    ſelves
    1.99
     snart
    1.91
     stata
    1.91
    栒
    1.89
    mentioned
    1.89
    Läs
    1.85
    Activations Density 0.004%

    No Known Activations