© 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. 75512
    Prev
    Next
    INDEX
    Explanations

    financial results and change

    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
     adversely
    -0.74
    くちゃ
    -0.73
     fået
    -0.71
    áním
    -0.69
     möglichst
    -0.69
    급
    -0.69
     định
    -0.69
     récup
    -0.68
    Šaltiniai
    -0.67
     erschien
    -0.67
    POSITIVE LOGITS
     positive
    1.96
    positive
    1.63
    Positive
    1.49
     Positive
    1.43
     black
    1.27
     positivo
    1.26
     profitable
    1.23
     positiven
    1.22
    POSITIVE
    1.20
     schwarze
    1.15
    Activations Density 0.027%

    No Known Activations