© 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. 5392
    Prev
    Next
    INDEX
    Explanations

    javascript click events

    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
    olites
    2.30
    goed
    2.23
     aquifers
    2.19
    branes
    2.18
    antiti
    2.14
    蚣
    2.14
    텁
    2.10
    icots
    2.08
     zeolite
    2.02
    yesters
    2.02
    POSITIVE LOGITS
     mov
    1.21
     edit
    1.18
    旋
    1.18
     dext
    1.17
     event
    1.16
     click
    1.13
     grab
    1.12
     inser
    1.12
     motion
    1.09
     PAS
    1.07
    Activations Density 0.002%

    No Known Activations