© 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. 15391
    Prev
    Next
    INDEX
    Explanations

    sturdy or flimsy

    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
    焄
    -2.39
    
    -2.30
     ``
    -2.17
    son
    -2.13
    菝
    -2.11
    ኧ
    -2.09
    
    -2.09
    ꯶
    -1.98
    𝄆
    -1.97
    攆
    -1.91
    POSITIVE LOGITS
    ’,
    2.80
    所谓的
    2.14
    必要な
    2.13
    〜〜
    2.13
    1
    2.08
    ’.
    2.02
     zerst
    1.94
    –
    1.94
     ersche
    1.92
    );
    1.88
    Activations Density 0.004%

    No Known Activations