© 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. 8964
    Prev
    Next
    INDEX
    Explanations

    doing/designed/directing/explaining

    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
     )।
    2.00
    Ⴀ
    1.99
     :).
    1.92
    矗
    1.83
    رسٹ
    1.81
     പാറ
    1.80
    神奇
    1.80
     pabc
    1.80
    Abasis
    1.80
     leapt
    1.80
    POSITIVE LOGITS
    ly
    1.48
    mal
    1.25
    -
    1.23
    ning
    1.18
    smöglichkeiten
    1.09
    ningar
    1.06
    এসসি
    1.04
     n
    1.02
    teen
    0.99
    nya
    0.98
    Activations Density 0.000%

    No Known Activations