© 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-262K
    7. 5058
    Prev
    Next
    INDEX
    Explanations

    neither nor else

    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
     vs
    0.48
    vs
    0.44
    FS
    0.41
    但是在
    0.39
    ВС
    0.38
    effectuer
    0.38
    Ε
    0.38
    iris
    0.38
    ifi
    0.37
     एस
    0.37
    POSITIVE LOGITS
     Neither
    0.61
     কিংবা
    0.56
    Neither
    0.56
     neither
    0.55
     Nor
    0.54
     Nope
    0.50
    那种
    0.48
     aquela
    0.47
     nor
    0.46
    那
    0.46
    Activations Density 0.098%

    No Known Activations