© 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. 21994
    Prev
    Next
    INDEX
    Explanations

    words beginning names/terms

    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
    
    -4.13
    {
    -3.45
    ]
    -3.31
     zulassen
    -3.19
    
    -3.06
    神
    -3.05
     feststellen
    -2.75
    푣
    -2.73
    还是很
    -2.72
    砹
    -2.72
    POSITIVE LOGITS
    as
    2.75
    
    2.72
    薷
    2.69
    ні
    2.41
    餮
    2.41
    幛
    2.36
     whom
    2.36
    <
    2.34
     Any
    2.33
     Also
    2.31
    Activations Density 0.000%

    No Known Activations