© 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. 148035
    Prev
    Next
    INDEX
    Explanations

    sequences ending in specific words

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

    criteria and other languages

    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
    込
    0.41
    حات
    0.39
    委会
    0.39
     spolupr
    0.38
    cooled
    0.38
     പ്രസി
    0.38
    ชั่น
    0.37
     orthodox
    0.37
     рис
    0.37
    はや
    0.37
    POSITIVE LOGITS
     którą
    0.43
    ógł
    0.39
     بولی
    0.38
     CLAIM
    0.38
    ရာ
    0.38
    겁
    0.37
     смерти
    0.37
     ngôn
    0.37
     choć
    0.37
     言っ
    0.37
    Activations Density 0.000%

    No Known Activations