© 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. 6157
    Prev
    Next
    INDEX
    Explanations

    Publish, compose, update, subscribe

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

    verbs of action and creation

    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
    ಾಮ
    0.50
     Colombe
    0.48
    uerung
    0.48
    splitted
    0.47
    transformation
    0.46
     Fleming
    0.46
    ADDED
    0.45
    闓
    0.45
     Chevalier
    0.45
    看到的
    0.45
    POSITIVE LOGITS
     Publish
    0.71
     Subscribe
    0.69
     Compose
    0.69
     generalize
    0.67
     Bake
    0.66
    Subscribe
    0.66
     Acquire
    0.66
    deployRoot
    0.65
     Modify
    0.64
     टीच
    0.63
    Activations Density 0.353%

    No Known Activations