© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13634
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    𝐫
    3.00
    ت
    2.90
    𝐤
    2.86
    決して
    2.51
    せん
    2.48
    র্গে
    2.47
    ﻳ
    2.47
    ял
    2.42
    icer
    2.35
     interment
    2.35
    POSITIVE LOGITS
     balanceOf
    3.47
    ઓ
    3.31
    ו
    2.98
     xay
    2.87
    ನ್ನು
    2.84
    ির
    2.83
    ු
    2.82
    т
    2.73
    τια
    2.67
    ווי
    2.66
    Activations Density 0.597%

    No Known Activations