© 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. 131000
    Prev
    Next
    INDEX
    Explanations

    code structure 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
    ȣ
    -0.84
     brinde
    -0.82
    
    -0.82
     แดง
    -0.82
     ਨੂੰ
    -0.82
    慫
    -0.81
    พ์
    -0.81
     upang
    -0.81
    entially
    -0.81
     talaga
    -0.79
    POSITIVE LOGITS
    lq
    0.84
    していますが
    0.83
     depuis
    0.83
     股份
    0.81
    Although
    0.78
     although
    0.77
     Although
    0.75
    rą
    0.75
     reflexionar
    0.74
     If
    0.74
    Activations Density 0.045%

    No Known Activations