© 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. 34074
    Prev
    Next
    INDEX
    Explanations

    stratified sampling

    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
    us
    1.20
    на
    1.02
    ية
    0.97
    ef
    0.95
    és
    0.84
    v
    0.84
    IG
    0.82
    S
    0.80
    ep
    0.79
    ey
    0.78
    POSITIVE LOGITS
    ו
    1.13
    ।
    1.10
     concili
    1.09
     stratified
    1.05
     strat
    1.05
    し
    1.04
     obowiąz
    1.01
     stratification
    1.00
     اینکه
    0.95
    。
    0.94
    Activations Density 0.002%

    No Known Activations