© 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. 54821
    Prev
    Next
    INDEX
    Explanations

    lists, formulas, and abbreviations

    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
     involves
    0.42
    固
    0.41
    চ্চ
    0.41
     ①
    0.40
     nguyên
    0.39
     Pred
    0.39
    Lower
    0.39
    Pred
    0.39
     
    0.39
    ABOR
    0.39
    POSITIVE LOGITS
     たち
    0.45
    ალა
    0.44
    ädig
    0.44
    甚至是
    0.42
    wiches
    0.40
    숑
    0.40
     തുടങ്ങിയ
    0.39
     appunto
    0.39
    🙃
    0.39
    🤓
    0.39
    Activations Density 0.047%

    No Known Activations