© 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-65K
    7. 11430
    Prev
    Next
    INDEX
    Explanations

    so followed by descriptor

    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_65k_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
    ó
    1.02
    و
    0.88
    此
    0.87
    ल
    0.79
    y
    0.79
    وغ
    0.76
    nél
    0.76
    ن
    0.74
    ो
    0.73
     I
    0.71
    POSITIVE LOGITS
    an
    1.05
    ва
    1.01
     an
    0.93
    ان
    0.89
    ма
    0.80
     that
    0.80
    ber
    0.79
     it
    0.79
    that
    0.78
     он
    0.78
    Activations Density 0.033%

    No Known Activations