© 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. 159819
    Prev
    Next
    INDEX
    Explanations

    technical development and instructions

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

    code dependencies configuration

    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
    rology
    0.42
    떡
    0.41
    athon
    0.40
    ouro
    0.39
    ●
    0.39
    লাভ
    0.38
    anesulfonyl
    0.38
    ー
    0.38
    et
    0.38
    ায়
    0.38
    POSITIVE LOGITS
     пове
    0.45
     путь
    0.45
    чів
    0.42
     جاس
    0.41
     nage
    0.41
    verfahren
    0.41
     парази
    0.40
    ಮಗೆ
    0.39
     قادر
    0.39
     تو
    0.39
    Activations Density 0.000%

    No Known Activations