© 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-16K
    7. 11625
    Prev
    Next
    INDEX
    Explanations

    what follows

    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
     do
    0.41
     Surprisingly
    0.41
     disposal
    0.40
    )}.
    0.40
     formar
    0.39
     उनकी
    0.39
     вообще
    0.38
     хуже
    0.38
    SORT
    0.37
    zuoye
    0.37
    POSITIVE LOGITS
    ាម
    0.46
    вався
    0.43
     ಶತ
    0.39
    StoredKeys
    0.39
    カップ
    0.37
    ্যাড
    0.37
    奈良
    0.37
    ܫ
    0.37
    Cuánto
    0.36
    山田
    0.36
    Activations Density 0.094%

    No Known Activations