© 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. 4323
    Prev
    Next
    INDEX
    Explanations

    describe or description

    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
    ت
    3.12
    dehyde
    3.02
    ुसार
    2.85
    ಿ
    2.74
     distinguishers
    2.72
    ᴡ
    2.68
     discre
    2.64
    ueta
    2.57
    िब
    2.54
    CHEMY
    2.54
    POSITIVE LOGITS
    𝐬
    2.36
     “”
    2.23
    ened
    2.23
     spong
    2.19
    Municipio
    2.11
     રીતે
    2.11
     bê
    2.07
    𝐮
    2.07
    𝐥
    2.04
    OrCallback
    2.04
    Activations Density 0.605%

    No Known Activations