© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3356
    Prev
    Next
    INDEX
    Explanations

    Brian Froud Tax implications

    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_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
     whatnot
    0.42
     dissonance
    0.35
     reproductive
    0.33
     can
    0.31
    기
    0.30
     সুরক্ষা
    0.30
    꿉
    0.30
     abstra
    0.30
     synthesis
    0.29
    opardy
    0.29
    POSITIVE LOGITS
    ０
    0.49
    wellery
    0.47
    postion
    0.46
    0.45
     ها
    0.44
    ↵↵
    0.44
    teilt
    0.43
     الحره
    0.43
    mselves
    0.43
    页面存档备份
    0.42
    Activations Density 1.050%

    No Known Activations