© 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. 16-GEMMASCOPE-2-RES-262K
    7. 144136
    Prev
    Next
    INDEX
    Explanations

    x86_64 arch

    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_16_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
    ب
    0.61
    াস
    0.59
    اع
    0.59
     Counc
    0.55
    Пер
    0.55
    ﺻ
    0.54
    ἤ
    0.54
    אַ
    0.52
    don
    0.52
    чек
    0.52
    POSITIVE LOGITS
     anderen
    0.64
     lager
    0.55
     andere
    0.55
     mattis
    0.54
     osob
    0.53
     hoger
    0.53
     ouders
    0.52
     altre
    0.52
     innebär
    0.51
     nau
    0.50
    Activations Density 0.000%

    No Known Activations