© 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. 31-GEMMASCOPE-2-RES-262K
    7. 101613
    Prev
    Next
    INDEX
    Explanations

    The Jed Foundation

    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
    ঠাৎ
    0.42
     intención
    0.41
     buts
    0.40
    意
    0.39
    ம்ச
    0.39
     swells
    0.38
    лум
    0.38
    ັງ
    0.37
    aksud
    0.37
     carro
    0.37
    POSITIVE LOGITS
     for
    0.50
     Applic
    0.44
     Heating
    0.43
     மாசுபா
    0.43
     remote
    0.43
    㳓
    0.42
     недели
    0.42
    Ε
    0.42
    STRING
    0.42
    strongly
    0.42
    Activations Density 0.006%

    No Known Activations