© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201684
    Prev
    Next
    INDEX
    Explanations

    best practices for structure and scale

    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_31_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
     infrastructure
    0.56
     infrastructural
    0.54
     speed
    0.51
     vibrate
    0.51
     already
    0.50
     fees
    0.50
     investments
    0.49
    િ
    0.48
     costs
    0.48
     commission
    0.47
    POSITIVE LOGITS
    rét
    0.55
    核心
    0.48
    构
    0.48
     Sé
    0.47
     río
    0.47
     División
    0.47
    atelli
    0.46
    André
    0.45
     Те
    0.45
    læ
    0.45
    Activations Density 0.001%

    No Known Activations