© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13073
    Prev
    Next
    INDEX
    Explanations

    page numbers followed by of

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

    page or slide 1

    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_31_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
    ли
    0.64
     elastic
    0.49
     zá
    0.47
     suboptimal
    0.47
    క్య
    0.47
    డ
    0.47
    ung
    0.46
     silica
    0.46
     mora
    0.46
    ка
    0.46
    POSITIVE LOGITS
     ITEMIZED
    0.47
    ຂອງ
    0.46
     ہیں
    0.45
     числі
    0.43
     следующее
    0.42
    vić
    0.42
     丿
    0.41
     பக்கம்
    0.41
    Pending
    0.41
     குறித்து
    0.41
    Activations Density 0.025%

    No Known Activations