© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60238
    Prev
    Next
    INDEX
    Explanations

    microkernel

    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_all/layer_41_width_262k_l0_big
    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
     SalesLT
    0.44
    })^
    0.42
    歎
    0.40
     своим
    0.39
    })}{\
    0.39
     рядом
    0.37
    ⵛ
    0.37
     katva
    0.36
     ভ্রম
    0.36
     ܡ
    0.36
    POSITIVE LOGITS
     multip
    0.46
    multip
    0.41
    Multip
    0.41
    need
    0.40
    Need
    0.40
    Multiple
    0.40
    需要
    0.39
     état
    0.39
    毕
    0.39
    ෑ
    0.39
    Activations Density 0.005%

    No Known Activations