© 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. 136257
    Prev
    Next
    INDEX
    Explanations

    deducted or subtracted 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_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
     hardening
    0.40
    追加
    0.39
    тва
    0.38
    AddComponent
    0.37
     پھیل
    0.36
    ["
    0.36
     mél
    0.36
     زنج
    0.36
    쩔
    0.35
    inertia
    0.35
    POSITIVE LOGITS
     deducted
    1.77
     deducting
    1.74
     deductions
    1.70
     deduct
    1.61
     subtracting
    1.60
     deduction
    1.59
     subtract
    1.58
     subtracted
    1.56
    扣
    1.53
     Subtract
    1.48
    Activations Density 0.036%

    No Known Activations