© 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. 11737
    Prev
    Next
    INDEX
    Explanations

    expecting questions or conditions

    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
    tad
    0.98
     नही
    0.96
    ವಹ
    0.96
    чее
    0.94
     اسر
    0.93
    డ
    0.93
    цы
    0.91
    collisions
    0.90
    ﾁ
    0.90
    crystal
    0.90
    POSITIVE LOGITS
    后缀
    1.17
     denomin
    1.15
    Names
    1.12
     designations
    1.12
     nombres
    1.12
     nomenclatura
    1.11
     surnames
    1.09
     shorthand
    1.08
     abbreviations
    1.08
     अभियांत्रिकी
    1.07
    Activations Density 0.006%

    No Known Activations