© 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-262K
    7. 24020
    Prev
    Next
    INDEX
    Explanations

    past/last

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

    recent past events

    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
     more
    0.47
    ,
    0.47
    <sup>
    0.46
    <sub>
    0.46
    à
    0.45
    ↵↵
    0.44
     scarcely
    0.44
     homozygous
    0.44
    <start_of_image>
    0.43
     Hig
    0.43
    POSITIVE LOGITS
     گزشتہ
    0.58
     vergang
    0.56
     afgelopen
    0.55
    昨
    0.52
     senaste
    0.50
     получения
    0.50
     получение
    0.50
     حصول
    0.50
     지난
    0.50
     الماضي
    0.50
    Activations Density 0.000%

    No Known Activations