© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14312
    Prev
    Next
    INDEX
    Explanations

    dates and days

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

    URLs and local paths

    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
     hoặc
    0.42
     உருவாக
    0.40
     derivadas
    0.40
    <unused2179>
    0.39
     vrsta
    0.39
    ווי
    0.39
     représentent
    0.39
     arba
    0.38
     paquetes
    0.38
     주로
    0.38
    POSITIVE LOGITS
     Annual
    0.48
    Annual
    0.45
    当时的
    0.44
    當時
    0.39
     वेबसाईट
    0.38
    当时
    0.38
     Archived
    0.37
    ளிடையே
    0.37
    衾
    0.36
     Metcalf
    0.36
    Activations Density 0.144%

    No Known Activations