© 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. 5346
    Prev
    Next
    INDEX
    Explanations

    filtering invalid rows

    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
    移除
    1.37
     energia
    1.36
    lett
    1.32
     энергия
    1.31
     энергии
    1.31
    kost
    1.30
    傳
    1.29
    石頭
    1.28
     husk
    1.28
    ToExp
    1.28
    POSITIVE LOGITS
     wristwatch
    1.09
    ophthal
    1.05
     synovial
    1.01
     oscilloscope
    1.01
     زینت
    1.00
     maxill
    1.00
     EEOC
    0.97
     debugging
    0.96
    ijkl
    0.96
     sagittal
    0.96
    Activations Density 0.041%

    No Known Activations