© 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. 151558
    Prev
    Next
    INDEX
    Explanations

    make or be able to

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

    explaining what can happen

    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
     refunded
    0.46
     firmly
    0.46
     elektronic
    0.45
     articulating
    0.43
    ﻌ
    0.43
     wisely
    0.41
     strategically
    0.41
     itemList
    0.41
     PEL
    0.41
     ventilated
    0.41
    POSITIVE LOGITS
     نداشت
    0.52
    有问题
    0.50
     зависимости
    0.49
     చేరు
    0.49
     කොට
    0.49
    Helpers
    0.48
     داش
    0.46
    ნდა
    0.46
    ก
    0.46
     нужно
    0.46
    Activations Density 0.000%

    No Known Activations