© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187124
    Prev
    Next
    INDEX
    Explanations

    tokens following common words

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

    collecting and providing

    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
    Negative Logits
     reacting
    0.51
    當時
    0.51
    反應
    0.50
    ylob
    0.45
     réaction
    0.43
    ব্ল
    0.43
     replying
    0.42
    oticons
    0.42
    ⇰
    0.42
    ids
    0.42
    POSITIVE LOGITS
     நிதி
    0.46
    <unused977>
    0.45
     temperatura
    0.44
     температуры
    0.44
    Демо
    0.43
     والع
    0.43
     гео
    0.41
     opportunità
    0.41
     esercizi
    0.41
    お金
    0.40
    Activations Density 0.005%

    No Known Activations