© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 204964
    Prev
    Next
    INDEX
    Explanations

    computational setup and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cómo
    0.39
     Абра
    0.38
     이건
    0.38
    Convert
    0.38
    新型
    0.38
     Cara
    0.37
    ܂
    0.37
    Ỉ
    0.36
    Abstract
    0.35
    Portal
    0.35
    POSITIVE LOGITS
     uu
    0.43
     amen
    0.43
    來越
    0.39
    டித்து
    0.37
    咉
    0.37
    astikan
    0.37
     tanggal
    0.36
    ્વાસ
    0.36
     awaken
    0.35
    ব্যাপ
    0.35
    Activations Density 0.000%

    No Known Activations