© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19611
    Prev
    Next
    INDEX
    Explanations

    implementing active concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    メージ
    0.43
     kest
    0.39
    rous
    0.39
    ڃ
    0.39
     distin
    0.38
     ngunit
    0.38
     Cependant
    0.38
     เอ่อ
    0.38
     fejl
    0.37
     neither
    0.37
    POSITIVE LOGITS
     적극
    0.43
    荠
    0.43
     использовать
    0.42
    యిత
    0.42
     মুহাম্ম
    0.42
     Zentrum
    0.41
    ötet
    0.41
     implementar
    0.40
     Methodology
    0.40
     активно
    0.39
    Activations Density 0.022%

    No Known Activations