© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60704
    Prev
    Next
    INDEX
    Explanations

    registering or enrolling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mélang
    -0.91
    lendi
    -0.90
    Wax
    -0.87
     réseaux
    -0.84
     Connexion
    -0.84
    Lovely
    -0.84
    魔
    -0.84
    IY
    -0.82
    Zack
    -0.82
     forêts
    -0.82
    POSITIVE LOGITS
     as
    1.47
     with
    1.44
     for
    1.39
     Register
    1.30
     registers
    1.27
     registering
    1.26
     registration
    1.23
     注册
    1.22
     at
    1.21
     register
    1.21
    Activations Density 0.041%

    No Known Activations