© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    related to frequent repetition

    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
     kitt
    1.67
     Counc
    1.66
    lığ
    1.63
    慮
    1.60
    ا۔
    1.55
     distancing
    1.55
    虑
    1.54
     مشاهد
    1.54
    🤒
    1.54
    🌧
    1.54
    POSITIVE LOGITS
    urate
    1.79
    brecht
    1.79
    RIO
    1.77
    ine
    1.69
    deut
    1.68
    iners
    1.68
    aboard
    1.67
    atet
    1.67
    ultaneous
    1.67
    ueroa
    1.66
    Activations Density 0.007%

    No Known Activations