© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98345
    Prev
    Next
    INDEX
    Explanations

    value of sum discounted

    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
    ີ່
    0.48
     ignored
    0.41
     theses
    0.41
    ="<?
    0.39
     Geschichte
    0.38
    ობა
    0.38
     принад
    0.38
    loadtxt
    0.38
    //"
    0.38
    ignored
    0.38
    POSITIVE LOGITS
    ott
    0.45
     combien
    0.44
    WAY
    0.39
    辦法
    0.38
     comprends
    0.37
     szyb
    0.37
     mores
    0.36
    クラス
    0.36
     umi
    0.36
    समझ
    0.36
    Activations Density 0.001%

    No Known Activations