© 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. 9301
    Prev
    Next
    INDEX
    Explanations

    yogurt, Directorate, entry, ask

    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
    perluan
    2.58
    asidd
    2.50
     Simón
    2.44
    紝
    2.37
    oleč
    2.35
    ৃতি
    2.35
     unittest
    2.34
    痹
    2.27
    irmingham
    2.26
    arcz
    2.23
    POSITIVE LOGITS
    prize
    1.92
    prises
    1.90
     into
    1.87
    prise
    1.87
    porn
    1.85
    prising
    1.83
    pite
    1.80
    入了
    1.77
    nie
    1.74
    pil
    1.72
    Activations Density 0.291%

    No Known Activations