© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8370
    Prev
    Next
    INDEX
    Explanations

    truth and facts

    np_acts-logits-general · gemini-2.5-flash-lite

    facts and factual information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    iophene
    0.36
    ரைய
    0.36
    깽
    0.35
    こだわり
    0.33
     रौनक
    0.32
    ંટ
    0.32
     বাঙ্গাল
    0.32
     মৌসুম
    0.31
    ⴱ
    0.31
    缦
    0.31
    POSITIVE LOGITS
     facts
    4.44
     Facts
    4.09
    facts
    4.06
    Facts
    3.98
     fakta
    3.89
     FACTS
    3.89
    事实
    3.88
    Fact
    3.66
     фак
    3.66
     Fact
    3.61
    Activations Density 0.164%

    No Known Activations