© 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. 246359
    Prev
    Next
    INDEX
    Explanations

    clients, management, estates, toilet seat

    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
     Buffalo
    0.47
     Vampire
    0.47
     Wasn
    0.46
    زمت
    0.45
     Zombie
    0.44
    某个
    0.43
     luch
    0.43
    痈
    0.43
     Bake
    0.42
     Dinosaur
    0.42
    POSITIVE LOGITS
    𝗙
    0.52
    Depuis
    0.49
    Famil
    0.48
     possibles
    0.47
    𝗨
    0.47
    ladı
    0.47
    FromThe
    0.47
    𝗚
    0.46
    Header
    0.45
     Depuis
    0.45
    Activations Density 0.002%

    No Known Activations