© 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. 2501
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    /
    1.27
     With
    1.03
    ,
    1.03
     /
    0.99
     Two
    0.98
     On
    0.97
     After
    0.96
     Is
    0.95
     TI
    0.92
     The
    0.91
    POSITIVE LOGITS
    ൻസ്
    1.29
    πά
    1.23
     হইত
    1.20
    ával
    1.15
    𝚌
    1.14
    頂いた
    1.13
    ítom
    1.12
    लाम
    1.11
    kprop
    1.11
    ində
    1.11
    Activations Density 0.012%

    No Known Activations