© 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. 48814
    Prev
    Next
    INDEX
    Explanations

    progressive [noun]

    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
    )=>{
    -0.94
     ferocious
    -0.93
     immense
    -0.93
    </strong>
    -0.90
     rechte
    -0.89
     nötig
    -0.87
     hugely
    -0.86
     praktisch
    -0.86
     gorgeous
    -0.84
     principalement
    -0.84
    POSITIVE LOGITS
    progressive
    1.24
     Progressive
    1.20
    Progressive
    1.08
    纜
    1.02
     يول
    1.01
     hukuman
    1.00
    寰
    0.98
    理念
    0.98
     stages
    0.96
    𝘁
    0.96
    Activations Density 0.022%

    No Known Activations