© 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. 124086
    Prev
    Next
    INDEX
    Explanations

    python import statements

    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
    Ꮏ
    -2.45
    ophageal
    -2.45
    ↵↵
    -2.11
    Öl
    -2.09
    嗵
    -2.02
     mépris
    -1.98
    ą
    -1.97
     gedachten
    -1.94
    퐹
    -1.91
    
    -1.91
    POSITIVE LOGITS
    .”
    2.80
    (
    2.33
     nebst
    2.31
    .,
    2.23
    ,.
    2.19
     Hinblick
    2.13
    }
    2.08
     ofrecerte
    1.99
    The
    1.98
     einschließlich
    1.96
    Activations Density 0.014%

    No Known Activations