© 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. 95356
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

    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
    ède
    -0.96
    >().
    -0.89
    verifyException
    -0.85
    竟然是
    -0.85
    TestingModule
    -0.85
     jugend
    -0.83
    MutableLiveData
    -0.82
    ####
    -0.81
     willkommen
    -0.81
     →
    -0.80
    POSITIVE LOGITS
    dalam
    0.89
    matig
    0.89
     REFUND
    0.85
    hadapi
    0.84
     useRef
    0.82
    ผลิต
    0.82
     sulfu
    0.81
     hoặc
    0.81
     ATOM
    0.81
    íp
    0.81
    Activations Density 0.002%

    No Known Activations