© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 242935
    Prev
    Next
    INDEX
    Explanations

    hut style; disability insurance

    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
    ında
    0.47
     lâm
    0.47
    ığında
    0.46
     ফাইন
    0.45
     kuk
    0.45
    öra
    0.45
    adou
    0.44
    :
    0.44
     начинается
    0.43
     वॉइस
    0.43
    POSITIVE LOGITS
    VITY
    0.47
    யின்
    0.45
    क्सन
    0.45
    前から
    0.45
    ベート
    0.44
    愍
    0.44
    禁
    0.44
     सलीम
    0.42
    ↵↵
    0.42
     fidèle
    0.42
    Activations Density 0.001%

    No Known Activations