© 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. 17-GEMMASCOPE-2-RES-16K
    4. 1898
    Prev
    Next
    INDEX
    Explanations

    join with spaces

    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
     стаўкі
    1.14
    őbb
    1.08
     नृत्य
    1.08
    뢰
    1.07
     주변
    1.07
    लील
    1.06
    每次
    1.06
     luyện
    1.05
     পুস্ত
    1.03
    每一次
    1.01
    POSITIVE LOGITS
    ''.
    1.10
     Essa
    1.04
     అంటున్నారు
    1.01
     Paloma
    0.98
     indeed
    0.98
     Allora
    0.97
     якобы
    0.95
     Huh
    0.94
     Donovan
    0.94
    嘍
    0.93
    Activations Density 0.429%

    No Known Activations