© 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. 138802
    Prev
    Next
    INDEX
    Explanations

    looking for words after

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

    input prompts

    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
    an
    0.52
     gasp
    0.51
    anath
    0.48
     cts
    0.47
    edt
    0.47
    athon
    0.47
     (**
    0.46
    arino
    0.46
     Marathon
    0.46
     cps
    0.45
    POSITIVE LOGITS
    Expansion
    0.54
     לי
    0.49
     Пан
    0.47
    Expanding
    0.47
     Чар
    0.46
     확장
    0.46
    特定の
    0.44
    로
    0.44
    🔝
    0.44
     کوي
    0.43
    Activations Density 0.000%

    No Known Activations