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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36693
    Prev
    Next
    INDEX
    Explanations

    `post` edits

    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
     perturbations
    0.37
     diel
    0.37
    更加
    0.36
     papillary
    0.35
    分析
    0.35
     perturb
    0.33
    ੲ
    0.33
     analysing
    0.33
     emphasises
    0.33
     nostra
    0.33
    POSITIVE LOGITS
     miraculously
    0.36
     Collin
    0.35
    =>$
    0.35
     Yakima
    0.34
     каби
    0.34
    рів
    0.33
     원하는
    0.33
     Vision
    0.33
    ടും
    0.33
    ිරි
    0.33
    Activations Density 0.002%

    No Known Activations