© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    neural network input design

    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
     قيمه
    1.58
     pertenece
    1.53
     giusta
    1.49
     เดือน
    1.49
     เหล
    1.48
    ەس
    1.45
     reconhe
    1.44
    茧
    1.42
     عزیز
    1.41
     altri
    1.40
    POSITIVE LOGITS
     approach
    2.00
    approach
    1.88
    式
    1.86
    式の
    1.84
     versus
    1.83
     방식
    1.78
    式的
    1.74
    タイプの
    1.71
     vs
    1.69
     strategy
    1.68
    Activations Density 1.080%

    No Known Activations