© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25827
    Prev
    Next
    INDEX
    Explanations

    i want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    0.54
    on
    0.52
    are
    0.46
     nám
    0.45
    都
    0.44
     collectively
    0.44
    -
    0.43
     нам
    0.42
    тесь
    0.41
    ？
    0.41
    POSITIVE LOGITS
     myself
    1.05
     دارم
    0.92
     Myself
    0.79
     خودم
    0.77
     نفسي
    0.77
     mijn
    0.75
     کنم
    0.75
     我的
    0.74
     мои
    0.74
    我自己
    0.73
    Activations Density 0.171%

    No Known Activations