© 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. 145356
    Prev
    Next
    INDEX
    Explanations

    muscle pain

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

    specific information about entities

    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
    StudentNo
    0.49
     وتق
    0.49
    ﻗ
    0.46
    блоки
    0.46
    стан
    0.45
    itik
    0.45
    聃
    0.45
    閎
    0.44
     pice
    0.44
    迨
    0.44
    POSITIVE LOGITS
     নৃশংস
    0.48
     memperhatikan
    0.48
     mengunjungi
    0.45
    ástico
    0.45
     comentó
    0.43
     hefyd
    0.43
     також
    0.43
     semelhante
    0.43
     পূর্ববাংলার
    0.42
    ']),
    0.42
    Activations Density 0.000%

    No Known Activations