© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32311
    Prev
    Next
    INDEX
    Explanations

    adding impurities or other elements

    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_40_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
    睾
    0.44
    lastCursor
    0.43
    oclaw
    0.43
    jResponse
    0.43
    プロダ
    0.43
    ября
    0.41
    رسٹ
    0.41
     Verfügung
    0.40
    战士
    0.40
    痉
    0.40
    POSITIVE LOGITS
     alloying
    1.04
     impurities
    1.01
     impurity
    0.90
     doping
    0.83
     additions
    0.82
     dop
    0.78
     additives
    0.75
     admi
    0.73
    impurity
    0.72
     substitutional
    0.70
    Activations Density 0.015%

    No Known Activations