© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52804
    Prev
    Next
    INDEX
    Explanations

    nin, ninja, Ninomae, Nintex, Ninhursag

    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_40_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
     neigh
    0.43
     shared
    0.42
     moreover
    0.41
     sidebar
    0.40
    筛
    0.40
    ꯌ
    0.39
     atom
    0.38
     ڈاؤن
    0.37
     awkward
    0.37
     sidel
    0.37
    POSITIVE LOGITS
    Phương
    0.49
    Nin
    0.48
     Nin
    0.39
    寜
    0.39
    ERRORTYPE
    0.36
    ahmatullahi
    0.36
    POSITORY
    0.36
    ZONE
    0.34
    Pyrid
    0.34
    ful
    0.34
    Activations Density 0.010%

    No Known Activations