© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    is examined, will proceed, should happen

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

    programming language keywords & snippets

    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
    🙃
    0.35
    🤷
    0.34
     daí
    0.32
     addirittura
    0.32
     ට
    0.32
    🤞
    0.32
     idk
    0.31
    监管
    0.31
     loke
    0.31
    薅
    0.31
    POSITIVE LOGITS
     নিঃসন্দেহে
    0.43
     paradox
    0.41
     প্রথমেই
    0.41
     सर्वप्रथम
    0.38
     undoubtedly
    0.38
     সর্বপ্রথম
    0.38
     innumerable
    0.38
     azonban
    0.37
     అనేక
    0.37
     one
    0.35
    Activations Density 0.400%

    No Known Activations