© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 260679
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ँ
    0.46
     discerned
    0.45
     réalisées
    0.44
     evaluations
    0.44
     praises
    0.44
     boutique
    0.43
    ต
    0.43
    偲
    0.42
     потребу
    0.40
    ዩ
    0.40
    POSITIVE LOGITS
     ஓடுப
    0.49
    QTTR
    0.47
     एसिड
    0.47
     trục
    0.47
     Warning
    0.46
     নীচে
    0.46
     jPanel
    0.45
     Jdbc
    0.45
     Piping
    0.45
     ඉක්
    0.45
    Activations Density 0.004%

    No Known Activations