© 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. 18504
    Prev
    Next
    INDEX
    Explanations

    first and middle names

    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
     وغيرها
    0.54
    और
    0.53
    य़ा
    0.51
    ماية
    0.51
    <unused356>
    0.51
    <unused1645>
    0.51
    <unused383>
    0.51
    <unused702>
    0.51
    <unused2156>
    0.50
     बीबी
    0.50
    POSITIVE LOGITS
     Edward
    0.63
     William
    0.61
     John
    0.60
     J
    0.59
     Robert
    0.56
     Joseph
    0.55
     Michael
    0.53
    Edward
    0.50
    ine
    0.49
    us
    0.49
    Activations Density 0.003%

    No Known Activations