© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167329
    Prev
    Next
    INDEX
    Explanations

    create database

    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
     پیغم
    0.44
     한다는
    0.43
     estabelecimento
    0.42
     جماعه
    0.41
     étrang
    0.41
    瀣
    0.40
    
    0.40
     quartier
    0.40
    amanho
    0.40
     comprador
    0.40
    POSITIVE LOGITS
    男女
    0.39
    挑选
    0.38
     unnoticed
    0.38
    itas
    0.36
     overlooked
    0.36
     rehe
    0.36
    rival
    0.35
    ure
    0.35
    ="//
    0.34
    mills
    0.34
    Activations Density 0.001%

    No Known Activations