© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29700
    Prev
    Next
    INDEX
    Explanations

    platypus lays eggs

    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
    RADIATION
    0.43
     möglicherweise
    0.42
    甾
    0.41
     disp
    0.40
     tıkl
    0.40
    氾
    0.39
    radiation
    0.39
     вследствие
    0.39
     Disp
    0.38
    showthread
    0.38
    POSITIVE LOGITS
    โครงการ
    0.43
    場合は
    0.41
     
    0.40
    것도
    0.39
    '=
    0.39
     projectId
    0.38
    =
    0.37
    ట్స్
    0.36
     現在
    0.35
    独特的
    0.35
    Activations Density 0.003%

    No Known Activations