© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58755
    Prev
    Next
    INDEX
    Explanations

    green light approval

    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
    設定
    -0.72
    옵
    -0.70
    Options
    -0.69
     numerose
    -0.68
    ASKET
    -0.68
     Clube
    -0.67
     pittura
    -0.66
     incontri
    -0.64
    destino
    -0.64
    dirkan
    -0.64
    POSITIVE LOGITS
     green
    2.53
     nod
    1.91
    green
    1.88
     thumbs
    1.88
     go
    1.77
     approval
    1.76
     okay
    1.63
     signal
    1.52
    GREEN
    1.48
     grü
    1.47
    Activations Density 0.027%

    No Known Activations