© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158981
    Prev
    Next
    INDEX
    Explanations

    assembly or installation

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

    shortage occupation

    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_31_width_262k_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
    спе
    0.46
     and
    0.45
    and
    0.45
     spec
    0.45
    à
    0.44
     punctu
    0.44
    闢
    0.44
    ᇁ
    0.44
    born
    0.42
    ੌਰ
    0.41
    POSITIVE LOGITS
     बीएसटीसी
    0.57
    抖
    0.56
    
    0.53
     LDGs
    0.52
     RAR
    0.50
     Adidas
    0.48
    BoxLayout
    0.48
    LVector
    0.48
    ermanfaat
    0.48
     minimize
    0.48
    Activations Density 0.001%

    No Known Activations