© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110890
    Prev
    Next
    INDEX
    Explanations

    "you learn" or "you say"

    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
     dumbass
    -1.17
     shite
    -1.12
     FUCK
    -1.11
     bullshit
    -1.11
     wtf
    -1.10
     motherfucker
    -1.09
     spektak
    -1.09
     SHIT
    -1.05
     WTF
    -1.05
     différents
    -1.04
    POSITIVE LOGITS
     könny
    0.99
    arxiv
    0.99
     delicately
    0.95
     menurun
    0.94
    Жизнь
    0.94
     classy
    0.93
     wzgl
    0.93
    いれば
    0.91
    After
    0.91
    +"/
    0.90
    Activations Density 0.125%

    No Known Activations