© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4196
    Prev
    Next
    INDEX
    Explanations

    anomaly detection, novel methods

    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
    上涨
    0.50
    吃饭
    0.47
    纽约
    0.47
    偿
    0.46
    行业的
    0.45
    律师
    0.45
    麻烦
    0.44
     پیسې
    0.44
    培训
    0.44
     cười
    0.44
    POSITIVE LOGITS
     nonlinear
    0.56
     homogeneous
    0.51
     synergistic
    0.48
     perturbed
    0.46
     unexplored
    0.46
     topological
    0.46
     uncertainties
    0.46
    ¡
    0.46
     hybrid
    0.45
     denoted
    0.44
    Activations Density 0.123%

    No Known Activations