© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24348
    Prev
    Next
    INDEX
    Explanations

    controller actions

    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
    ꩡ
    0.43
    逖
    0.42
     শিখে
    0.39
    Listen
    0.38
    离开
    0.37
    Flag
    0.37
     सिस्टम
    0.37
    Float
    0.36
     арифмети
    0.36
     Float
    0.35
    POSITIVE LOGITS
     w
    0.46
     roti
    0.43
     grains
    0.42
     allowance
    0.42
     butane
    0.42
    yesha
    0.41
     och
    0.41
     salt
    0.39
     agony
    0.39
     marshes
    0.38
    Activations Density 0.001%

    No Known Activations