© 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-65K
    7. 2771
    Prev
    Next
    INDEX
    Explanations

    an object, iterator, array, empty

    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_65k_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
    ل
    0.48
    ampilan
    0.46
    ли
    0.44
     anvä
    0.44
     använd
    0.43
    ständig
    0.43
     nonché
    0.43
     እንዲሁ
    0.42
     têm
    0.41
     exempel
    0.41
    POSITIVE LOGITS
    0.57
     a
    0.49
     you
    0.39
    Э
    0.38
     \
    0.38
     believe
    0.37
    A
    0.37
    V
    0.36
     District
    0.35
    ，
    0.33
    Activations Density 0.062%

    No Known Activations