© 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. 27828
    Prev
    Next
    INDEX
    Explanations

    text-to-image content generation

    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
     heinous
    0.46
     fera
    0.42
     PCB
    0.42
    ure
    0.42
     U
    0.42
     प्रौ
    0.42
     urinal
    0.42
     superstructure
    0.41
     NIC
    0.41
     Nxb
    0.41
    POSITIVE LOGITS
    情节
    0.47
    写
    0.46
    切
    0.45
     quyết
    0.45
    ولز
    0.44
    өлү
    0.43
     ajout
    0.43
     imitated
    0.43
    内容
    0.43
    随机
    0.43
    Activations Density 0.001%

    No Known Activations