© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13422
    Prev
    Next
    INDEX
    Explanations

    years later

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

    still

    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_16k_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
    துவாக
    0.46
    弇
    0.45
    しばらく
    0.45
     વખતે
    0.43
    一会儿
    0.43
     जीते
    0.43
    雩
    0.43
    近年来
    0.41
    soon
    0.41
    ทัน
    0.40
    POSITIVE LOGITS
     still
    1.18
     STILL
    1.11
     fortfarande
    1.05
    仍
    1.00
     Still
    0.95
    Still
    0.95
    still
    0.94
     vẫn
    0.94
     masih
    0.93
    依然
    0.92
    Activations Density 0.222%

    No Known Activations