© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32629
    Prev
    Next
    INDEX
    Explanations

    annual leave entitlement

    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_all/layer_41_width_262k_l0_big
    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
     informatique
    0.42
    ﻵ
    0.40
    ěn
    0.40
    ithing
    0.40
    squareup
    0.39
    aphone
    0.38
     chaîne
    0.38
    出
    0.38
    尿
    0.38
     архівів
    0.38
    POSITIVE LOGITS
     annual
    0.72
     entitlement
    0.68
     yearly
    0.64
     entitlements
    0.61
     anual
    0.57
    annual
    0.57
     statutory
    0.55
     entitle
    0.54
    每年
    0.54
     Annual
    0.53
    Activations Density 0.002%

    No Known Activations