© 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. 122435
    Prev
    Next
    INDEX
    Explanations

    both/and conjunctions

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

    both or duplicates

    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
    瞿
    0.44
    眄
    0.44
    र्तन
    0.43
     форму
    0.42
    รูป
    0.42
     сфор
    0.42
     सोचने
    0.42
     జరిగ
    0.41
    娥
    0.41
    Historic
    0.41
    POSITIVE LOGITS
     both
    0.54
     cả
    0.52
     både
    0.50
     también
    0.50
     zarówno
    0.49
     दोनों
    0.48
     pleasure
    0.48
     även
    0.46
     دونوں
    0.46
     sowohl
    0.45
    Activations Density 0.000%

    No Known Activations