© 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. 52127
    Prev
    Next
    INDEX
    Explanations

    Windows Server

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

    context disclosure

    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
    ตัน
    0.52
    ล
    0.48
    孃
    0.47
     seul
    0.47
    Throughout
    0.46
    რო
    0.46
    Franklin
    0.46
    ใน
    0.46
    Wheel
    0.46
    ла
    0.45
    POSITIVE LOGITS
    /[\
    0.52
    endum
    0.47
     လုပ်
    0.47
    iters
    0.46
     கூறப்படுகிறது
    0.45
    shows
    0.45
     ಆಹಾರ
    0.45
     കട
    0.45
    atter
    0.44
    のこと
    0.44
    Activations Density 0.001%

    No Known Activations