© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15571
    Prev
    Next
    INDEX
    Explanations

    numbers followed by text

    np_acts-logits-general · gemini-2.5-flash-lite

    stock price scoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     නිෂ්පා
    0.50
     सुनवाई
    0.49
     வீடியோ
    0.49
    मैन
    0.48
     मामूली
    0.48
    商品を
    0.47
     जूते
    0.46
    ጊ
    0.46
    ബു
    0.46
    으나
    0.46
    POSITIVE LOGITS
     sch
    0.49
     dez
    0.49
     gleichen
    0.48
     doğr
    0.48
     agglut
    0.48
     albo
    0.48
     bordered
    0.48
     plan
    0.47
     staircase
    0.47
     subsp
    0.47
    Activations Density 0.000%

    No Known Activations