© 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. 878
    Prev
    Next
    INDEX
    Explanations

    target audience

    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
     (_)
    1.66
     görev
    1.64
    予防
    1.64
     eszk
    1.62
    usky
    1.61
    ārt
    1.58
     polymerized
    1.58
    Documents
    1.58
    utth
    1.57
     <*>
    1.57
    POSITIVE LOGITS
     popularity
    2.36
     crowds
    2.17
     fanbase
    2.16
    popularity
    1.91
     crowd
    1.91
     viewership
    1.88
     audiences
    1.68
     acclaim
    1.68
     readership
    1.66
     audience
    1.64
    Activations Density 2.258%

    No Known Activations