© 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-262K
    7. 135189
    Prev
    Next
    INDEX
    Explanations

    network interface status

    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
    客様
    0.43
    叁
    0.41
    pcid
    0.40
     फल
    0.39
    }\{
    0.39
     కంప
    0.39
     பத்து
    0.38
    ंची
    0.38
     Lucie
    0.38
    ሶ
    0.38
    POSITIVE LOGITS
     broadcasts
    0.39
    ług
    0.38
     mtu
    0.37
    Proto
    0.37
    騷
    0.37
    Foreign
    0.36
     безопасности
    0.36
     UP
    0.36
    నో
    0.36
    scope
    0.36
    Activations Density 0.016%

    No Known Activations