© 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. 2478
    Prev
    Next
    INDEX
    Explanations

    actions with a bowl

    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
    <unused2012>
    1.21
    <unused309>
    1.19
    fromParams
    1.14
    <unused937>
    1.09
    <unused1768>
    1.08
    <unused353>
    1.08
    <unused2018>
    1.06
    <unused1653>
    1.06
    <unused1747>
    1.06
    <unused1729>
    1.05
    POSITIVE LOGITS
     sebanyak
    0.83
     nº
    0.79
     correspondiente
    0.79
     tanggal
    0.77
    ๋า
    0.75
     xác
    0.75
     запре
    0.73
    Germain
    0.73
    (
    0.72
     yaitu
    0.72
    Activations Density 0.200%

    No Known Activations