© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15674
    Prev
    Next
    INDEX
    Explanations

    temperature ranges

    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
     gênero
    1.15
    țile
    1.06
    ália
    1.06
    cja
    1.06
    ânica
    1.03
    â
    1.02
    。\
    1.01
    ía
    1.01
    izarra
    1.00
    âns
    1.00
    POSITIVE LOGITS
     退
    1.55
     半
    1.45
     えっと
    1.45
     又
    1.39
     完全
    1.36
     乳
    1.35
     場合
    1.34
     debuting
    1.33
     賞
    1.32
     اول
    1.30
    Activations Density 0.005%

    No Known Activations