© 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. 30700
    Prev
    Next
    INDEX
    Explanations

    key legal and government concepts

    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
    сят
    0.48
    >(_
    0.46
    你应该
    0.44
    کٹ
    0.41
    ,//
    0.41
    PickerController
    0.41
     nCmd
    0.40
    uchsia
    0.40
    ClearedBy
    0.40
    ↗
    0.40
    POSITIVE LOGITS
     o
    0.43
    werten
    0.43
     horseback
    0.41
     inclin
    0.40
     exemple
    0.40
     incl
    0.40
    跑步
    0.40
    ností
    0.39
     leu
    0.39
    running
    0.38
    Activations Density 0.006%

    No Known Activations