© 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. 182491
    Prev
    Next
    INDEX
    Explanations

    manufacturer supply

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

    reference number

    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
    公园
    0.53
     书
    0.48
     голу
    0.47
    盐
    0.45
    餐厅
    0.44
     வடிக
    0.44
     автобу
    0.43
    ("***
    0.43
     boulevard
    0.42
    戏
    0.42
    POSITIVE LOGITS
     emergencia
    0.45
    発展
    0.42
    機の
    0.42
     druga
    0.42
     Reihen
    0.41
     Nigerians
    0.41
     quell
    0.41
    žiť
    0.41
     Besitz
    0.41
    णारी
    0.40
    Activations Density 0.001%

    No Known Activations