© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9344
    Prev
    Next
    INDEX
    Explanations

    Dutch words like 'einde'

    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
     hay
    1.29
    oo
    1.26
    ेष
    1.25
     um
    1.22
     các
    1.19
     tiếp
    1.18
     sif
    1.16
    吠
    1.15
     tư
    1.15
     펼
    1.14
    POSITIVE LOGITS
    cerer
    1.66
    షి
    1.65
    Spy
    1.57
     लाए
    1.54
    AVE
    1.52
    আগ
    1.52
    ("\"
    1.51
    Optim
    1.49
     दर्शाता
    1.48
     resulting
    1.48
    Activations Density 0.000%

    No Known Activations