© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52551
    Prev
    Next
    INDEX
    Explanations

    computing system training and code

    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
    หรือ
    0.50
     או
    0.50
    甜蜜
    0.46
    もしくは
    0.45
     किंवा
    0.44
     ¿?
    0.44
    🥳
    0.44
    または
    0.43
     அல்லது
    0.43
    又は
    0.42
    POSITIVE LOGITS
     fewer
    0.45
    hi
    0.42
     Fewer
    0.39
    us
    0.38
    ie
    0.37
     lensing
    0.37
     পরই
    0.36
    denly
    0.35
     inilah
    0.35
    л
    0.35
    Activations Density 0.011%

    No Known Activations