© 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. 22-GEMMASCOPE-2-RES-16K
    7. 53
    Prev
    Next
    INDEX
    Explanations

    foreign greetings

    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
    ংখ্যান
    0.69
     považ
    0.66
     совер
    0.66
    ساعدة
    0.65
    堃
    0.64
    ázej
    0.64
     apreciar
    0.63
     zejména
    0.63
     wykorzyst
    0.63
    করণ
    0.63
    POSITIVE LOGITS
    hrs
    1.14
    0
    1.08
    5
    1.02
     hrs
    1.00
    km
    0.99
    Km
    0.97
    kms
    0.95
     weeks
    0.95
    mins
    0.94
    8
    0.93
    Activations Density 3.505%

    No Known Activations