© 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. 40-GEMMASCOPE-2-RES-262K
    7. 190975
    Prev
    Next
    INDEX
    Explanations

    ultimate example

    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_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
    ത്ഥ
    0.39
     Германия
    0.38
    窠
    0.38
    Deutschland
    0.38
    round
    0.37
    ंनी
    0.37
    讓
    0.37
    ٿ
    0.37
     majú
    0.37
    థ
    0.37
    POSITIVE LOGITS
    烜
    0.43
     lucu
    0.41
     छुटकारा
    0.39
     wytr
    0.38
     Patience
    0.38
     अपॉ
    0.37
    aspx
    0.37
     kumpulan
    0.36
     spotted
    0.36
     task
    0.36
    Activations Density 0.001%

    No Known Activations