© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3424
    Prev
    Next
    INDEX
    Explanations

    fish, weed, vegetation, creatures

    np_acts-logits-general · gemini-2.5-flash-lite

    species names and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     യൂണി
    0.52
    <unused24>
    0.51
    礽
    0.51
     আদালত
    0.50
     Millennials
    0.50
     Zayn
    0.50
    幼儿园
    0.49
    账户
    0.49
    踮
    0.48
     ponencia
    0.48
    POSITIVE LOGITS
    wort
    0.78
    weed
    0.72
    tail
    0.70
    fin
    0.68
     tailed
    0.68
     toad
    0.67
     dwarf
    0.66
     bush
    0.65
    back
    0.65
     eel
    0.64
    Activations Density 0.115%

    No Known Activations