© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14170
    Prev
    Next
    INDEX
    Explanations

    government data, incentives, regulations

    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_7_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
    äische
    2.04
    ടാ
    2.00
     पहिला
    1.97
    枃
    1.84
    いろいろ
    1.80
    liste
    1.76
     Novo
    1.75
     prvi
    1.73
     erstes
    1.73
     formée
    1.72
    POSITIVE LOGITS
     временем
    1.63
     subtracted
    1.59
    කු
    1.56
     overcrowding
    1.55
    ᴋ
    1.52
     посту
    1.51
     afterlife
    1.49
    ։
    1.48
     occurring
    1.47
     mathematically
    1.44
    Activations Density 0.000%

    No Known Activations