© 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. 22-GEMMASCOPE-RES-131K
    7. 71233
    Prev
    Next
    INDEX
    Explanations

    status indicators and states

    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_22/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
    —
    -1.07
    =
    -1.04
    -
    -0.94
    D
    -0.91
     ancora
    -0.90
    Ps
    -0.90
     līdz
    -0.90
    ViewBag
    -0.88
    returnValue
    -0.87
    常常
    -0.87
    POSITIVE LOGITS
     or
    1.16
    三個
    1.09
     veck
    1.09
    뭘
    1.08
    させて頂きます
    1.08
    してきました
    1.07
    したいと思います
    1.06
    諜
    1.05
    恥
    1.05
    我怎么
    1.05
    Activations Density 0.003%

    No Known Activations