© 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. 154807
    Prev
    Next
    INDEX
    Explanations

    context in technical documentation

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

    takes a list of samples

    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
    ௭
    0.45
    战
    0.45
    名稱
    0.44
    Seqlist
    0.42
    uetooth
    0.41
    戰
    0.41
    果
    0.41
    学习
    0.41
    車種
    0.41
     这些
    0.41
    POSITIVE LOGITS
     контек
    0.61
     context
    0.59
     kontek
    0.54
    context
    0.54
     Context
    0.52
     contesto
    0.49
     contexto
    0.49
     ctx
    0.48
    ctx
    0.47
    Context
    0.44
    Activations Density 0.005%

    No Known Activations