© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    programmed to refuse harmful requests

    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
    ançais
    1.09
    inars
    1.08
    issner
    1.01
     quadrupole
    0.99
     convertView
    0.98
    )[
    0.98
     shakes
    0.96
     Sow
    0.96
     milking
    0.96
     oligonucle
    0.95
    POSITIVE LOGITS
    記
    1.34
    సా
    1.33
    지가
    1.32
    狲
    1.32
    면
    1.32
    fähig
    1.31
    лизм
    1.30
     Radeon
    1.29
    지로
    1.27
    记
    1.27
    Activations Density 0.045%

    No Known Activations