© 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. 10259
    Prev
    Next
    INDEX
    Explanations

    html content

    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
    四
    1.36
     fours
    1.36
    4
    1.32
    4
    1.31
    ⁴
    1.26
     FOUR
    1.25
     four
    1.23
     fourth
    1.22
     quattro
    1.22
     quartet
    1.21
    POSITIVE LOGITS
     রবিবার
    0.86
    साई
    0.85
    onta
    0.85
     Tent
    0.84
    انج
    0.83
    urdu
    0.82
    卞
    0.82
    ালে
    0.81
     Jugendlichen
    0.80
    يان
    0.80
    Activations Density 0.127%

    No Known Activations