© 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. 236428
    Prev
    Next
    INDEX
    Explanations

    specified where

    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
     ,
    0.49
     صارفین
    0.46
    insol
    0.45
    最強
    0.45
    最高
    0.44
     gemstones
    0.44
     ज्वेल
    0.44
    、
    0.43
    いただく
    0.43
     apothe
    0.43
    POSITIVE LOGITS
    לי
    0.53
    ждение
    0.50
    Recent
    0.48
    তে
    0.48
    Instit
    0.48
    руппа
    0.48
     maxSize
    0.46
    Dise
    0.46
    סה
    0.45
    ждении
    0.45
    Activations Density 0.000%

    No Known Activations