© 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-262K
    7. 144186
    Prev
    Next
    INDEX
    Explanations

    severity level

    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
     IL
    0.52
     i
    0.49
     l
    0.47
     mango
    0.46
     bloody
    0.46
     salami
    0.46
     bird
    0.45
     sm
    0.45
     MAR
    0.44
     ste
    0.44
    POSITIVE LOGITS
    нії
    0.52
    افة
    0.52
    配置文件
    0.48
    简洁
    0.48
    ConfigFile
    0.48
    ლებელია
    0.47
    стоит
    0.46
    ={$
    0.46
    约束
    0.46
    StopTime
    0.46
    Activations Density 0.004%

    No Known Activations