© 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. 54431
    Prev
    Next
    INDEX
    Explanations

    streamer personalities, company cultures

    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
    可以
    0.46
     sabes
    0.46
    ▲
    0.45
    aminen
    0.44
     तभी
    0.43
     esiste
    0.43
    isek
    0.43
     बिक
    0.42
     sabe
    0.42
    有机会
    0.42
    POSITIVE LOGITS
     reportedly
    0.43
     distraught
    0.40
    ፊ
    0.40
    щины
    0.39
     promising
    0.38
     mourn
    0.37
     horrified
    0.37
     mour
    0.37
     Celebrate
    0.36
     comforting
    0.36
    Activations Density 0.002%

    No Known Activations