© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4543
    Prev
    Next
    INDEX
    Explanations

    Lily

    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_12_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
     conceptually
    1.12
     explicitly
    1.10
    สด
    1.03
     willfully
    1.02
    음
    0.99
    πέ
    0.97
     Taipei
    0.96
     Pyongyang
    0.96
     พิจ
    0.93
     schematically
    0.93
    POSITIVE LOGITS
    pkins
    1.90
    rets
    1.78
     teş
    1.78
    unts
    1.77
    ڈنگ
    1.77
     protectors
    1.77
    utu
    1.76
    쏠
    1.76
    umas
    1.76
     آشنا
    1.75
    Activations Density 0.008%

    No Known Activations