© 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. 193553
    Prev
    Next
    INDEX
    Explanations

    Tate Modern, Thames, Tower Bridge

    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
     Endowment
    0.40
     polo
    0.39
     QS
    0.39
     decidedly
    0.39
     Tommy
    0.39
     Avery
    0.38
    賦
    0.38
     Lone
    0.38
     jeweler
    0.38
     Diamond
    0.37
    POSITIVE LOGITS
     turbine
    0.64
     turbines
    0.50
     Turbine
    0.49
    turbine
    0.45
    拉克
    0.43
     switch
    0.42
    ]}/
    0.40
    Turb
    0.40
    ﭥ
    0.39
    切换
    0.39
    Activations Density 0.002%

    No Known Activations