© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6045
    Prev
    Next
    INDEX
    Explanations

    ports and connections

    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
    Sous
    1.00
    mods
    0.99
    ニス
    0.95
    스테
    0.93
    엡
    0.93
    noduch
    0.91
    ̉
    0.90
    
    0.89
    녹
    0.88
     inqui
    0.88
    POSITIVE LOGITS
    oms
    1.51
    oooooooo
    1.45
    poon
    1.44
    férence
    1.42
    oooo
    1.36
     tenfold
    1.35
    Bras
    1.34
    廈
    1.34
    早く
    1.34
    ступа
    1.34
    Activations Density 0.172%

    No Known Activations