© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100536
    Prev
    Next
    INDEX
    Explanations

    adjusting physical or abstract things

    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
     But
    -2.88
    ний
    -2.61
     astute
    -2.22
     embellished
    -2.20
     appe
    -2.16
     habría
    -2.13
    butuhkan
    -2.13
    }$
    -2.13
    en
    -2.08
    imantan
    -2.08
    POSITIVE LOGITS
    谞
    3.53
    ↵
    2.91
    Ⲉ
    2.73
    摃
    2.73
    橚
    2.63
    会儿
    2.55
    ⬯
    2.52
    芣
    2.45
    梘
    2.39
    
    2.38
    Activations Density 0.005%

    No Known Activations