© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70421
    Prev
    Next
    INDEX
    Explanations

    Cathedral or Petropole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    زش
    1.39
     Франция
    1.38
    당
    1.36
    unam
    1.32
     парла
    1.32
    depart
    1.30
    getRuntime
    1.29
     дей
    1.27
    соб
    1.26
    ᴵ
    1.26
    POSITIVE LOGITS
     voegen
    1.51
    ophilic
    1.41
     encouraging
    1.35
    aided
    1.33
    REFERENCES
    1.30
     Oral
    1.26
     digraph
    1.25
    ophiles
    1.25
     Helped
    1.23
    Yes
    1.22
    Activations Density 0.001%

    No Known Activations