© 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. 9003
    Prev
    Next
    INDEX
    Explanations

    6 followed by 2

    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
     non
    0.99
     an
    0.98
    ̀i
    0.97
    itively
    0.97
    ệm
    0.95
     “
    0.94
    ря
    0.94
    ,
    0.92
     (
    0.90
    ly
    0.89
    POSITIVE LOGITS
    <unused1079>
    1.54
    <unused164>
    1.46
     Punishment
    1.45
     TRANSPORTURI
    1.44
    <unused1804>
    1.42
    <unused1993>
    1.42
    <unused582>
    1.41
    <unused294>
    1.39
    <unused1749>
    1.39
    <unused1151>
    1.38
    Activations Density 0.012%

    No Known Activations