© 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. 9117
    Prev
    Next
    INDEX
    Explanations

    indicating contrast

    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
     ​​
    1.06
    ​.
    0.83
     নিয়
    0.82
    ゚
    0.81
    ​​
    0.76
     Throughout
    0.75
    onat
    0.74
    ⼤
    0.72
    <0xE2>
    0.72
     In
    0.70
    POSITIVE LOGITS
     lunatic
    1.63
     cadáver
    1.52
     idiot
    1.51
     stupid
    1.43
     wretched
    1.42
     dodgy
    1.41
     hideous
    1.41
     horr
    1.41
    (/*
    1.41
    *(
    1.40
    Activations Density 0.090%

    No Known Activations