© 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. 170066
    Prev
    Next
    INDEX
    Explanations

    rules, laws, business, lens

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

    swallowed whole

    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
    的热
    0.53
    fehlung
    0.51
    🩹
    0.47
     بعد
    0.47
    ഹ്
    0.45
    ösung
    0.45
     tangente
    0.45
    ifen
    0.44
    isometric
    0.44
     المرحله
    0.44
    POSITIVE LOGITS
    ।
    0.57
     Treats
    0.53
     Promises
    0.50
    s
    0.48
     WORKS
    0.47
     Priv
    0.46
    ה
    0.46
     Accompl
    0.46
     Haci
    0.46
    כ
    0.45
    Activations Density 0.000%

    No Known Activations