© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151817
    Prev
    Next
    INDEX
    Explanations

    obsolete, milk, purpose

    np_acts-logits-general · gemini-2.5-flash-lite

    operations, usage, day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manifestly
    0.45
     takım
    0.44
    걔
    0.44
    ຜະລິດຕະພັນ
    0.44
    гъл
    0.43
     실제로
    0.43
    ürü
    0.43
    ég
    0.42
     바꿔
    0.42
     잡
    0.42
    POSITIVE LOGITS
     VU
    0.43
     conseguenza
    0.37
     GE
    0.37
     सका
    0.36
    OCE
    0.36
     mapDispatch
    0.36
    工作中
    0.36
     Wu
    0.36
     মৃত্যুর
    0.36
     curcumin
    0.36
    Activations Density 0.002%

    No Known Activations