© 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. 177606
    Prev
    Next
    INDEX
    Explanations

    Christmas Special

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

    technical details

    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
     figlio
    0.49
    兒子
    0.48
    س
    0.47
     weiß
    0.47
     জর্জ
    0.46
     أعلى
    0.46
     allgemein
    0.44
     সমর্থ
    0.44
    িয়াস
    0.44
     uomo
    0.43
    POSITIVE LOGITS
     Passes
    0.49
     😄
    0.48
     Hatch
    0.47
    ampuan
    0.46
     ataupun
    0.46
     Plates
    0.46
    😄
    0.45
     Often
    0.44
     sınav
    0.44
    DateFormat
    0.44
    Activations Density 0.002%

    No Known Activations