© 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. 5572
    Prev
    Next
    INDEX
    Explanations

    we can or need

    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
    جة
    1.91
    ewater
    1.90
     Shaf
    1.89
    يمة
    1.83
    産業
    1.82
     tecnico
    1.82
    ڇ
    1.80
     verduras
    1.80
    ڄ
    1.80
     الإنسان
    1.77
    POSITIVE LOGITS
     oluşan
    0.92
    ủ
    0.88
     him
    0.83
     induced
    0.83
    vorm
    0.78
     오류
    0.74
    urbin
    0.73
    Anagram
    0.72
     mistaken
    0.71
    {~
    0.70
    Activations Density 0.004%

    No Known Activations