© 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. 57437
    Prev
    Next
    INDEX
    Explanations

    waypoint reached

    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
    ”—
    -2.28
    ).”
    -2.22
    ኧ
    -2.20
    ”,
    -2.00
     distinta
    -1.99
    !”
    -1.98
    ar
    -1.97
    。”
    -1.94
    )—
    -1.94
    ens
    -1.88
    POSITIVE LOGITS
    ஂ
    3.06
    耜
    2.73
    䛗
    2.70
    ᷆
    2.61
    鲧
    2.53
    UGHTER
    2.50
    
    2.44
    多年的
    2.41
    €™
    2.41
    
    2.36
    Activations Density 0.003%

    No Known Activations