© 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. 252621
    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
    變
    0.58
    про
    0.55
    при
    0.54
    父亲
    0.54
    变
    0.51
    ﺼ
    0.50
     funzioni
    0.50
    墮
    0.50
    Multicolored
    0.49
    ઞ
    0.49
    POSITIVE LOGITS
     closets
    0.47
     dryers
    0.46
     outsourcing
    0.46
     autopilot
    0.45
     collaborations
    0.45
     holdings
    0.44
     freezes
    0.44
     offshoring
    0.43
     worries
    0.43
     freezing
    0.42
    Activations Density 0.000%

    No Known Activations