© 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. 73197
    Prev
    Next
    INDEX
    Explanations

    linear scaling

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

    universally applicable

    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
     mosquitoes
    0.43
    껏
    0.43
     mosquito
    0.41
     झालेल्या
    0.40
    Govern
    0.40
     ground
    0.38
    Lone
    0.38
     تعین
    0.38
     criterion
    0.38
     airplane
    0.37
    POSITIVE LOGITS
    🫢
    0.55
    poque
    0.54
    ╕
    0.53
    ってい
    0.52
     รวมถึง
    0.52
     архіви
    0.50
    愫
    0.49
     💞
    0.49
    𝒊
    0.48
     świecie
    0.48
    Activations Density 0.002%

    No Known Activations