© 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. 7790
    Prev
    Next
    INDEX
    Explanations

    eating food

    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
    He
    1.52
    Cre
    1.52
    #"
    1.43
    ണ്ടാ
    1.43
    Maria
    1.39
    ußer
    1.39
     skyl
    1.39
    Have
    1.38
    ruh
    1.37
     handed
    1.37
    POSITIVE LOGITS
    stuffs
    2.51
    糰
    2.17
    餮
    2.13
    🍚
    2.09
    grain
    2.09
    intestinal
    2.06
    を食べ
    1.97
    armonic
    1.91
    erno
    1.90
    grains
    1.89
    Activations Density 0.455%

    No Known Activations