© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204850
    Prev
    Next
    INDEX
    Explanations

    provide efficiency and awareness

    np_acts-logits-general · gemini-2.5-flash-lite

    slower processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    л
    0.53
    有两个
    0.51
    совой
    0.48
    肌肉
    0.46
    巡
    0.46
    产生了
    0.44
    сной
    0.44
    赛季
    0.44
     تعريف
    0.44
    TimeZone
    0.44
    POSITIVE LOGITS
     commenters
    0.51
     inadequ
    0.46
     aren
    0.45
    alter
    0.45
     Mouth
    0.44
     سکتے
    0.44
    ↵↵
    0.43
     Eee
    0.43
     Flatten
    0.42
     save
    0.42
    Activations Density 0.000%

    No Known Activations