© 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. 222474
    Prev
    Next
    INDEX
    Explanations

    AHA melting

    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
     seventeenth
    0.42
    फ्टर
    0.39
    ╩
    0.39
    ở
    0.39
    Perc
    0.38
     obowią
    0.37
    ajit
    0.37
    系
    0.37
    colorChoice
    0.37
     chanted
    0.37
    POSITIVE LOGITS
     Skyrim
    0.41
     Melting
    0.40
     wisely
    0.40
    粨
    0.40
     melting
    0.39
     endExpNow
    0.38
     জ্ঞানী
    0.37
     AsyncStorage
    0.36
     limited
    0.36
    溶
    0.36
    Activations Density 0.001%

    No Known Activations