© 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. 11700
    Prev
    Next
    INDEX
    Explanations

    recent years

    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
    য়াম
    1.73
    ləşdirilib
    1.53
    鈕
    1.48
    ittaa
    1.47
    ueba
    1.42
    setlength
    1.41
     பெற
    1.39
    embourg
    1.39
    erequisites
    1.39
     Cram
    1.37
    POSITIVE LOGITS
    പ്പിച്ച്
    1.25
     outta
    1.23
    恋愛
    1.20
    moil
    1.20
     buoy
    1.18
     flagged
    1.16
    침
    1.16
     hearts
    1.16
    रान
    1.16
     cheered
    1.15
    Activations Density 0.000%

    No Known Activations