© 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-65K
    7. 30027
    Prev
    Next
    INDEX
    Explanations

    explaining or indicating amounts

    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_65k_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
     karena
    0.44
    தால்
    0.42
    觸
    0.40
    触
    0.39
    re
    0.39
     peut
    0.39
     Reforma
    0.39
    覚
    0.39
    The
    0.38
     தீவிர
    0.38
    POSITIVE LOGITS
     contiguous
    0.45
    しないで
    0.44
     uptime
    0.43
     NOT
    0.43
     όχι
    0.43
     بجائے
    0.43
    👏👏👏👏
    0.43
     যানবাহন
    0.42
     পাইনি
    0.42
     ছিলাম
    0.42
    Activations Density 0.030%

    No Known Activations