© 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. 258
    Prev
    Next
    INDEX
    Explanations

    . subjects

    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
     be
    0.93
     ex
    0.89
     "
    0.89
     “
    0.87
     cos
    0.86
     mass
    0.84
     stay
    0.82
     support
    0.82
     go
    0.81
    ,
    0.81
    POSITIVE LOGITS
    文件夹
    1.65
    folder
    1.64
    フォルダ
    1.57
    Readme
    1.50
    tochrome
    1.50
    widget
    1.49
    xml
    1.48
    idx
    1.47
    index
    1.46
    filename
    1.45
    Activations Density 0.383%

    No Known Activations