© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1821
    Prev
    Next
    INDEX
    Explanations

    code structure and technical terms

    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_17_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
    нию
    0.91
     lisa
    0.89
     etc
    0.87
    +(
    0.84
     dob
    0.84
    人の
    0.83
    等
    0.83
    人が
    0.83
     +(
    0.80
    tas
    0.79
    POSITIVE LOGITS
     abelian
    1.23
    énom
    1.12
    Begriffsklär
    1.11
    Doming
    1.07
     matemático
    1.06
    Swami
    1.01
     Abelian
    1.00
     algéb
    0.99
    Gerald
    0.99
     izdel
    0.99
    Activations Density 0.074%

    No Known Activations