© 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. 210777
    Prev
    Next
    INDEX
    Explanations

    how something is

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

    inflatable pillow

    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
     ekstra
    0.52
    Intro
    0.48
     terrenos
    0.48
    卿
    0.48
     Intro
    0.47
     anggota
    0.46
    สรร
    0.46
    Multimedia
    0.46
     kurs
    0.45
     matahari
    0.45
    POSITIVE LOGITS
    ăți
    0.52
    ৩
    0.50
     bettors
    0.46
     وړاندوینې
    0.46
     photoelectric
    0.44
     PDC
    0.44
     جوړونکی
    0.44
    raron
    0.43
     PCD
    0.43
    見る
    0.42
    Activations Density 0.001%

    No Known Activations