© 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. 78689
    Prev
    Next
    INDEX
    Explanations

    mathematics and languages

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

    domains complementing LLMs and React

    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
     elevated
    0.50
     ব্যাক্ত
    0.47
    effective
    0.46
     LEC
    0.45
     बचाया
    0.45
     കൂടുതല്‍
    0.44
     Бүгенге
    0.44
    ⟤
    0.44
     Nicolson
    0.44
     hxg
    0.44
    POSITIVE LOGITS
    يرين
    0.52
     في
    0.50
     يا
    0.48
    *
    0.48
    في
    0.48
     تصميم
    0.48
    <sup>
    0.47
     لي
    0.47
    جين
    0.46
    Reserve
    0.46
    Activations Density 0.001%

    No Known Activations