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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 34
    Prev
    Next
    INDEX
    Explanations

    knowing or understanding something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Evidence
    0.32
     检测
    0.32
     многочис
    0.31
    evidence
    0.30
    ДУ
    0.30
    olí
    0.30
     обнару
    0.30
    ଏ
    0.30
     evidencia
    0.29
    මට
    0.28
    POSITIVE LOGITS
     about
    0.63
     intimately
    0.56
     firsthand
    0.55
     instinctively
    0.55
     whereof
    0.52
     अबाउट
    0.46
     tentang
    0.46
     perfectly
    0.46
     better
    0.44
     intellectually
    0.44
    Activations Density 0.308%

    No Known Activations