© 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. 100710
    Prev
    Next
    INDEX
    Explanations

    online or descriptions

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

    parallel railway tracks

    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
     dè
    0.51
    FTA
    0.46
     observe
    0.45
     rouge
    0.44
     oversaw
    0.44
     beobachten
    0.43
    仞
    0.43
    ፍተኛ
    0.43
    ંને
    0.43
     obserw
    0.43
    POSITIVE LOGITS
    ลาย
    0.47
     पहला
    0.47
    slideTo
    0.45
    ก
    0.45
    стояние
    0.44
     pharmacists
    0.44
     эфи
    0.44
     Mexico
    0.43
    ชีพ
    0.43
     ограни
    0.42
    Activations Density 0.000%

    No Known Activations