© 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-65K
    7. 54810
    Prev
    Next
    INDEX
    Explanations

    explaining things, kindness, growth

    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
     hazardous
    0.44
     pathologies
    0.43
    ഢ
    0.42
     paham
    0.41
     frontier
    0.40
     nightclubs
    0.40
     tyrannical
    0.40
     वांछ
    0.39
    ;
    0.39
     grueling
    0.39
    POSITIVE LOGITS
    被人
    0.52
    及时
    0.48
    老师
    0.47
    鼓励
    0.46
    小朋友
    0.45
    其实
    0.44
     από
    0.44
     लोगों
    0.43
    别人的
    0.42
    也很
    0.42
    Activations Density 0.016%

    No Known Activations