© 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. 47304
    Prev
    Next
    INDEX
    Explanations

    special or future topics

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

    diverse geology, force of, versatile reagents

    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
     ગયો
    0.50
     ઝ
    0.49
    ળ
    0.46
     против
    0.46
     દ્વા
    0.45
     thiểu
    0.45
    جمالي
    0.44
    ಝ
    0.44
     gdzie
    0.43
     thí
    0.43
    POSITIVE LOGITS
    会在
    0.54
    会有
    0.52
     Bento
    0.50
    将会
    0.48
    这些
    0.47
    จะมี
    0.47
    ination
    0.46
    एंगे
    0.46
    bfs
    0.46
    䅞
    0.46
    Activations Density 0.000%

    No Known Activations