© 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. 137049
    Prev
    Next
    INDEX
    Explanations

    intuition telling you, development important

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

    problems and thinking

    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
     :"
    0.57
     weltweit
    0.54
     etiqu
    0.53
     ensu
    0.52
     dünya
    0.49
     especial
    0.48
     хоть
    0.48
     Über
    0.47
     cicl
    0.47
     WHO
    0.46
    POSITIVE LOGITS
    п
    0.47
    ξε
    0.45
    নিজ
    0.41
    ring
    0.41
    село
    0.41
    dock
    0.41
    这种情况
    0.40
    內部
    0.39
    𝐡
    0.39
    उथ
    0.38
    Activations Density 0.002%

    No Known Activations