© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30891
    Prev
    Next
    INDEX
    Explanations

    sticky

    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_all/layer_41_width_262k_l0_big
    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
    ytical
    0.39
    樎
    0.39
     मतदारसं
    0.38
    隐含
    0.37
    كس
    0.36
     ज्योति
    0.36
     cranking
    0.36
     kř
    0.35
     raies
    0.35
    及时
    0.35
    POSITIVE LOGITS
     sticky
    1.51
    Sticky
    1.51
     Sticky
    1.51
    sticky
    1.47
    黏
    1.31
    粘
    1.26
     adhesive
    1.01
     Stick
    1.00
     stick
    0.98
     glue
    0.93
    Activations Density 0.004%

    No Known Activations