© 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. 66167
    Prev
    Next
    INDEX
    Explanations

    lists positive qualities

    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
     it
    -1.77
     like
    -1.50
    }$
    -1.37
     Loads
    -1.30
     Preferably
    -1.24
    ТЕЛЬ
    -1.20
     ...,
    -1.19
     realizzata
    -1.19
    》,
    -1.19
    ๖
    -1.16
    POSITIVE LOGITS
    </strong>
    1.81
    喽
    1.67
    缡
    1.40
    pantalon
    1.35
     artık
    1.35
    الدرا
    1.33
    呎
    1.31
     последу
    1.31
    now
    1.30
    際の
    1.28
    Activations Density 0.020%

    No Known Activations