© 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. 112934
    Prev
    Next
    INDEX
    Explanations

    foreign language or technical jargon

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

    context length

    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
    ёт
    0.52
    掳
    0.51
    は
    0.50
    President
    0.46
    生の
    0.45
     President
    0.44
    E
    0.44
    预计
    0.44
    회
    0.44
    坤
    0.43
    POSITIVE LOGITS
     rodzaju
    0.54
     gravy
    0.49
     preced
    0.49
     intermediates
    0.48
     procesos
    0.48
     dále
    0.48
     processes
    0.47
     flavors
    0.47
     ISPs
    0.47
     whitish
    0.47
    Activations Density 0.001%

    No Known Activations