© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3323
    Prev
    Next
    INDEX
    Explanations

    release/liberation

    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_15_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
     trigo
    1.24
    剃
    1.22
    ほうが
    1.20
     dugout
    1.19
    Worked
    1.18
     woodwork
    1.18
    AndroidJUnit
    1.16
    早在
    1.16
    drawString
    1.15
     herringbone
    1.15
    POSITIVE LOGITS
     excl
    1.01
    监狱
    1.01
    cooled
    0.99
    acion
    0.95
    rins
    0.94
     Demons
    0.94
    
    0.93
    rasi
    0.91
    ダム
    0.91
    hões
    0.90
    Activations Density 0.031%

    No Known Activations