© 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. 2626
    Prev
    Next
    INDEX
    Explanations

    programmed to be a safe

    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
     caranya
    1.16
    げ
    1.09
     содержания
    1.08
     ὑ
    1.04
    strlen
    1.04
     grd
    1.01
     вър
    1.01
     wajib
    0.99
    argc
    0.99
     있지만
    0.98
    POSITIVE LOGITS
    拐
    1.28
     set
    1.16
     excepted
    1.11
     series
    1.11
    eru
    1.10
     switching
    1.10
     tipping
    1.10
     switched
    1.09
     terminating
    1.09
     exception
    1.09
    Activations Density 0.048%

    No Known Activations