© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3623
    Prev
    Next
    INDEX
    Explanations

    add or adding

    np_acts-logits-general · gemini-2.5-flash-lite

    adding or appending elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    /******/
    0.37
    widet
    0.36
    ائر
    0.36
    सीय
    0.35
    యాన్ని
    0.34
    ैर्य
    0.34
    ioutil
    0.33
    槃
    0.33
    ιτε
    0.32
    тесь
    0.32
    POSITIVE LOGITS
     add
    3.97
     Add
    3.80
    add
    3.78
    Add
    3.69
     добавля
    3.69
     adding
    3.66
     добав
    3.63
    添加
    3.61
     добавить
    3.59
     ADD
    3.56
    Activations Density 0.647%

    No Known Activations