© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 51
    Prev
    Next
    INDEX
    Explanations

    code blocks `if`, `else`, `begin`

    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_22_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
    மாகவும்
    1.00
    liğini
    0.89
    arschijnlijk
    0.88
    '])]
    0.84
    可能是
    0.84
    yip
    0.84
     rispond
    0.84
     dignit
    0.83
     동시에
    0.83
    片的
    0.83
    POSITIVE LOGITS
     {
    2.72
    {
    2.20
     {//
    2.03
     {...
    1.91
     {.
    1.84
     {}
    1.79
     {/*
    1.69
     {\
    1.69
    {//
    1.63
     {,
    1.63
    Activations Density 0.813%

    No Known Activations