© 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. 9208
    Prev
    Next
    INDEX
    Explanations

    for [time period]

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

    durations of years, decades, centuries

    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
    ('-',
    0.46
     असल्यास
    0.44
     použ
    0.43
    })=\
    0.42
     若
    0.42
    সঙ্ঘ
    0.42
     adicionales
    0.42
    ococcal
    0.41
    㗁
    0.41
    を追加
    0.41
    POSITIVE LOGITS
     years
    1.55
     decades
    1.39
    很久
    1.31
    years
    1.30
     años
    1.28
     jaren
    1.25
     centuries
    1.24
    几年
    1.23
     yıll
    1.21
     months
    1.19
    Activations Density 0.150%

    No Known Activations