© 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. 124841
    Prev
    Next
    INDEX
    Explanations

    parents

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

    phrases following specific words

    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
    就要
    0.43
    要是
    0.42
    弄
    0.41
    들이
    0.41
    不出
    0.40
     중에
    0.39
    螯
    0.39
    রিতে
    0.38
    㶲
    0.38
    一定要
    0.38
    POSITIVE LOGITS
     Algunos
    0.44
     ടി
    0.44
    ड्स
    0.41
     اسرائی
    0.41
    entiti
    0.41
    ęp
    0.41
    ethe
    0.41
     defaultConfig
    0.41
     several
    0.40
     Ende
    0.40
    Activations Density 0.001%

    No Known Activations