© 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. 2284
    Prev
    Next
    INDEX
    Explanations

    ensure ability or readiness

    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
    呛
    1.57
    岔
    1.47
     offending
    1.44
    壅
    1.44
    ành
    1.39
     unterschiedlich
    1.38
     agrav
    1.37
    猥
    1.36
     آدمی
    1.34
    旖
    1.32
    POSITIVE LOGITS
    放心
    1.61
     مطم
    1.52
     rely
    1.50
     Rely
    1.50
     fiducia
    1.49
     trusts
    1.45
     confiance
    1.45
    TRUST
    1.44
     trust
    1.44
     assurance
    1.41
    Activations Density 0.518%

    No Known Activations