© 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. 84135
    Prev
    Next
    INDEX
    Explanations

    saying

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

    jokes and riddles

    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
     lessening
    0.47
    私たちの
    0.39
     weakening
    0.38
     Inhibition
    0.37
     decreases
    0.37
    חר
    0.37
    ！
    0.37
     ভালোবাসি
    0.36
    чів
    0.36
     BLOOD
    0.36
    POSITIVE LOGITS
     egregious
    0.45
     üç
    0.43
     cem
    0.39
    gruntled
    0.39
     இரண்டு
    0.38
    ộp
    0.38
    齟
    0.38
     órg
    0.38
    sqlite
    0.37
     armchair
    0.37
    Activations Density 0.073%

    No Known Activations