© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    aren't you?

    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
    ими
    2.01
    кать
    1.93
    <unused869>
    1.90
     实
    1.89
    asaddo
    1.89
    atthanam
    1.88
    rageBet
    1.87
    atthane
    1.87
     攵
    1.84
    eleSp
    1.84
    POSITIVE LOGITS
    n
    2.16
    sa
    1.87
     n
    1.62
    s
    1.59
    r
    1.57
    down
    1.49
     simbolo
    1.48
    <0x92>
    1.46
     miro
    1.44
     ordin
    1.43
    Activations Density 0.064%

    No Known Activations