© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    Warning, may cause

    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
     coco
    1.09
    amazing
    1.04
     Gems
    1.02
     too
    1.02
    ::::::
    0.99
    incredible
    0.98
     happy
    0.97
    otri
    0.96
    too
    0.96
     gems
    0.95
    POSITIVE LOGITS
    かつ
    1.41
     upon
    1.39
    ному
    1.26
     navigating
    1.24
    在这个
    1.22
    以後
    1.19
    тному
    1.17
    在這個
    1.15
     façon
    1.15
    於
    1.14
    Activations Density 0.000%

    No Known Activations