© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    still / continue / remain

    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
    GoAbroad
    0.43
    ம்பி
    0.37
     kolei
    0.37
    λλ
    0.35
    лізу
    0.35
    б
    0.34
    잦
    0.34
    俪
    0.34
     pula
    0.33
     मल्टीप्लाई
    0.33
    POSITIVE LOGITS
     still
    4.00
    still
    3.53
    Still
    3.45
     vẫn
    3.44
    仍然
    3.41
     STILL
    3.38
     Still
    3.33
     fortfarande
    3.30
    仍
    3.22
    依然
    3.19
    Activations Density 0.852%

    No Known Activations