© 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. 151353
    Prev
    Next
    INDEX
    Explanations

    New York, remind me, dollars

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

    focus on specifics

    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
     હેઠળ
    0.52
     содержания
    0.48
    д
    0.46
     sayıda
    0.46
    Jurassic
    0.46
    会的
    0.44
    尽
    0.44
     prze
    0.43
     વિશ્વ
    0.43
    ⚭
    0.43
    POSITIVE LOGITS
     publie
    0.49
     spør
    0.43
     public
    0.42
    চাই
    0.41
     defenses
    0.39
    匯
    0.39
     treasury
    0.38
    駁
    0.38
    講解
    0.38
     desire
    0.37
    Activations Density 0.000%

    No Known Activations