© 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. 76264
    Prev
    Next
    INDEX
    Explanations

    proxy sits

    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
    墀
    0.41
     Cauchy
    0.39
    στι
    0.37
     suficientemente
    0.37
    ٱ
    0.37
     Recognizing
    0.37
     sufficiently
    0.36
    黠
    0.36
    спекти
    0.36
     ausreichend
    0.36
    POSITIVE LOGITS
     tetap
    0.47
     simile
    0.45
     send
    0.44
    cud
    0.43
     essentially
    0.43
     izd
    0.43
     বিনিম
    0.43
     ownership
    0.42
     sale
    0.42
     huk
    0.41
    Activations Density 0.127%

    No Known Activations