© 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. 22954
    Prev
    Next
    INDEX
    Explanations

    events happening

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

    new, ancient, working, happening

    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
    RESS
    0.44
     ஆகியோர்
    0.43
     imassa
    0.43
     όπου
    0.42
     scorer
    0.41
     เนื่องจาก
    0.41
     ซึ่ง
    0.41
     ซ
    0.40
    人數
    0.40
     necessaria
    0.40
    POSITIVE LOGITS
     happening
    0.77
     happened
    0.72
    的东西
    0.66
     Happened
    0.65
     happen
    0.61
     Happens
    0.59
     happens
    0.58
     ঘটেছে
    0.58
     aconteceu
    0.57
     ঘটছে
    0.55
    Activations Density 0.356%

    No Known Activations