© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7130
    Prev
    Next
    INDEX
    Explanations

    protection against

    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
    Negative Logits
     puntual
    1.47
    沧
    1.39
    炅
    1.36
    قیق
    1.36
    appy
    1.35
    cog
    1.33
     telescop
    1.32
    ">(
    1.31
    愉
    1.31
    polish
    1.30
    POSITIVE LOGITS
     against
    5.61
    against
    5.53
     Against
    5.10
     AGAINST
    5.07
    Against
    4.35
     contre
    3.99
     ضد
    3.72
     contra
    3.30
     против
    3.25
     gegen
    3.17
    Activations Density 0.259%

    No Known Activations