© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57514
    Prev
    Next
    INDEX
    Explanations

    launching new initiatives

    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
    それも
    -1.13
     mogą
    -1.08
     aufgestellt
    -1.06
    Rather
    -1.00
     growing
    -0.98
     Rather
    -0.96
     crescente
    -0.96
    decreasing
    -0.94
     raging
    -0.94
     puisqu
    -0.94
    POSITIVE LOGITS
     into
    2.27
     initiatives
    1.54
     продаж
    1.52
     onto
    1.47
     campaigns
    1.38
     hostilities
    1.36
     launched
    1.34
     campaign
    1.20
     with
    1.16
     website
    1.16
    Activations Density 0.023%

    No Known Activations