© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4590
    Prev
    Next
    INDEX
    Explanations

    programming documentation structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MAD
    1.55
    ácia
    1.49
     Madsen
    1.49
    ῆ
    1.48
     Maz
    1.46
     وز
    1.45
    cloud
    1.44
    мена
    1.43
    PC
    1.43
     Zab
    1.43
    POSITIVE LOGITS
    につきまして
    1.08
    !!”
    1.05
    !!
    1.02
    🥺
    1.00
    !!!!!!
    0.99
    小编
    0.96
    !!!
    0.95
    !!!!
    0.95
    știg
    0.94
    我们将
    0.93
    Activations Density 0.013%

    No Known Activations