© 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-65K
    7. 19981
    Prev
    Next
    INDEX
    Explanations

    superintelligence surpasses human

    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
    各大
    0.45
    oubliez
    0.44
    ମ୍
    0.44
    aians
    0.44
    aseti
    0.44
    ᱪ
    0.44
    𝗷
    0.43
    撗
    0.43
    metall
    0.43
    IUS
    0.43
    POSITIVE LOGITS
     lobster
    0.48
    นะ
    0.41
     report
    0.40
     steak
    0.39
     finding
    0.39
     Lobster
    0.39
     acknowledge
    0.38
     Ste
    0.38
     steering
    0.38
     punch
    0.37
    Activations Density 0.043%

    No Known Activations