© 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. 48747
    Prev
    Next
    INDEX
    Explanations

    so to speak

    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
    يم
    0.66
     \
    0.60
    يرة
    0.56
    يري
    0.54
     Wyn
    0.53
    葶
    0.52
    سمى
    0.52
    ير
    0.52
     Temper
    0.51
     particulier
    0.51
    POSITIVE LOGITS
    on
    0.69
    heavy
    0.64
     UIS
    0.64
    iculis
    0.64
    ን
    0.62
    failed
    0.60
    (´
    0.59
    the
    0.58
     மேம்ப
    0.58
    health
    0.56
    Activations Density 0.000%

    No Known Activations