© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 6611
    Prev
    Next
    INDEX
    Explanations

    sql and code structure

    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
    ):
    1.60
    )،
    1.48
    ),
    1.35
    !),
    1.28
    :',
    1.27
    ،
    1.26
    ,)
    1.24
    :,
    1.22
    .):
    1.21
    ,:
    1.21
    POSITIVE LOGITS
     kein
    1.38
     Nothing
    1.30
     Không
    1.27
     これは
    1.26
     Các
    1.23
     zwölf
    1.21
     keine
    1.21
     keinen
    1.19
     dwie
    1.18
     এখানকার
    1.18
    Activations Density 0.232%

    No Known Activations