© 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. 249150
    Prev
    Next
    INDEX
    Explanations

    suitable slot

    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
     অনুপ্রবেশ
    0.48
     ಜೀವನ
    0.47
     あなた
    0.45
     紅
    0.45
    すでに
    0.45
     individui
    0.45
    とり
    0.44
     একত্রে
    0.44
     axit
    0.44
     punctatis
    0.44
    POSITIVE LOGITS
    ()
    0.53
    ED
    0.51
    +
    0.50
     Grade
    0.49
     Properties
    0.49
    )
    0.49
    :
    0.49
     Facilities
    0.48
                
    0.48
     Phase
    0.46
    Activations Density 0.000%

    No Known Activations