© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10249
    Prev
    Next
    INDEX
    Explanations

    rabbit and bunny

    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_16k_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
     swept
    0.37
     anal
    0.37
     tes
    0.37
    칵
    0.36
     accents
    0.35
     $|\
    0.34
    PageState
    0.34
     cationic
    0.34
     закін
    0.34
    acad
    0.33
    POSITIVE LOGITS
     rabbit
    1.85
     Rabbit
    1.78
    Rabbit
    1.73
     rabbits
    1.62
     bunny
    1.59
    rabbit
    1.55
    🐰
    1.52
    兔
    1.46
    兔子
    1.44
    🐇
    1.43
    Activations Density 0.058%

    No Known Activations