© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16180
    Prev
    Next
    INDEX
    Explanations

    Agnes, pine, leak, exclusive

    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
    0.47
     O
    0.43
     arguably
    0.41
     twenty
    0.41
     S
    0.40
     hitherto
    0.40
     would
    0.39
     henüz
    0.39
     zou
    0.38
     wyd
    0.38
    POSITIVE LOGITS
    但
    0.49
    ї
    0.49
     деца
    0.48
    ಞ
    0.48
    镗
    0.48
    했지만
    0.48
     энерги
    0.47
    ба
    0.46
    人
    0.45
    руем
    0.45
    Activations Density 0.020%

    No Known Activations