© 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. 84494
    Prev
    Next
    INDEX
    Explanations

    reconstruction, reconciliation, reconnaissance

    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
    -3.64
     When
    -2.58
    )
    -2.56
    What
    -2.38
     Vorschriften
    -2.27
    How
    -2.25
     {
    -2.17
     Should
    -2.11
     With
    -2.09
     He
    -2.06
    POSITIVE LOGITS
    婠
    2.67
     tiroirs
    2.56
     poches
    2.55
    愎
    2.48
     carreaux
    2.48
     mauva
    2.47
     chambres
    2.44
    
    2.39
     pertes
    2.38
    檍
    2.34
    Activations Density 0.004%

    No Known Activations