© 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. 15775
    Prev
    Next
    INDEX
    Explanations

    ease, difficulty, or simplification

    np_acts-logits-general · gemini-2.5-flash-lite

    making things easier

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ד
    0.54
     ਚ
    0.49
     Մ
    0.47
     נ
    0.46
     ब
    0.46
     중요한
    0.45
     ਨ
    0.45
     ด
    0.45
    ्न
    0.45
     profunda
    0.45
    POSITIVE LOGITS
     Easier
    0.96
     easier
    0.91
     ease
    0.87
    Ease
    0.84
    ease
    0.82
     arduous
    0.79
     Ease
    0.78
    负担
    0.77
    eas
    0.77
     hardship
    0.76
    Activations Density 0.150%

    No Known Activations