© 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. 114622
    Prev
    Next
    INDEX
    Explanations

    foreign and non-English words

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

    detective figure, promise

    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
     r
    0.54
    nd
    0.45
     identical
    0.45
     layout
    0.44
     disgr
    0.44
     Reglamento
    0.43
     Seminary
    0.43
     lathes
    0.43
    recycle
    0.43
     Compiler
    0.43
    POSITIVE LOGITS
    Winters
    0.54
    新
    0.51
    меня
    0.49
    Mediterr
    0.48
    Doll
    0.48
    Stranger
    0.47
    コ
    0.47
     স্ম
    0.46
    Yeni
    0.46
    Chú
    0.46
    Activations Density 0.001%

    No Known Activations