© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1767
    Prev
    Next
    INDEX
    Explanations

    Gemma

    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_65k_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
    akili
    0.42
    akra
    0.37
    ัคร
    0.37
    ISK
    0.36
    avoz
    0.35
    爨
    0.35
    طيب
    0.34
    छाड़
    0.34
    粋
    0.34
    ক্ষণ
    0.34
    POSITIVE LOGITS
     G
    1.20
     g
    0.93
    G
    0.79
     گ
    0.73
     ग
    0.59
     ג
    0.59
     গ
    0.55
    g
    0.55
     GED
    0.54
    teborg
    0.54
    Activations Density 0.155%

    No Known Activations