© 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. 16022
    Prev
    Next
    INDEX
    Explanations

    User interface

    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
    ๐
    2.82
    ある
    2.80
    <unused1850>
    2.70
    s
    2.64
     Prony
    2.64
    <unused1754>
    2.63
    spired
    2.63
    लिये
    2.59
    VEMENT
    2.57
     multipart
    2.57
    POSITIVE LOGITS
    𝕣
    2.02
    age
    1.95
    னர்
    1.91
    weiter
    1.87
    heben
    1.85
    ug
    1.81
     프로
    1.80
    즈
    1.80
    kom
    1.80
    जरी
    1.79
    Activations Density 0.049%

    No Known Activations