© 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. 33367
    Prev
    Next
    INDEX
    Explanations

    precedential: non-precedential

    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
    ᶤ
    -0.86
    nosť
    -0.82
     birlikte
    -0.79
     {{$
    -0.78
    communication
    -0.76
     Mahi
    -0.76
     tark
    -0.75
     Crusoe
    -0.73
    pada
    -0.73
    erst
    -0.71
    POSITIVE LOGITS
     predeceased
    1.01
     grandparents
    0.82
     uncles
    0.79
     illustrating
    0.78
    '])){
    0.78
    nologue
    0.77
     :
    0.77
    ="">
    0.77
    zegorz
    0.77
    employeeId
    0.74
    Activations Density 0.001%

    No Known Activations