© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 163031
    Prev
    Next
    INDEX
    Explanations

    time or related phrases

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

    important details

    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_262k_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
     fro
    0.45
     masing
    0.44
     Torah
    0.44
     Adventist
    0.43
    ৈ
    0.43
     Pakistan
    0.42
    ள்ளதாக
    0.42
     Montessori
    0.41
     امی
    0.41
     architecture
    0.41
    POSITIVE LOGITS
     paramètres
    0.53
    ímav
    0.50
    膑
    0.50
    autions
    0.49
    账号
    0.49
    账
    0.49
    τητα
    0.48
    笂
    0.47
    注意事项
    0.46
    參數
    0.46
    Activations Density 0.001%

    No Known Activations