© 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. 104291
    Prev
    Next
    INDEX
    Explanations

    rolls and purchases

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

    evaluating performance and infrastructure

    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
    يت
    0.54
    sites
    0.52
    民间
    0.51
    साइट
    0.49
    тів
    0.49
     Amérique
    0.48
    ⚉
    0.47
     जितना
    0.47
    糁
    0.47
     caminos
    0.47
    POSITIVE LOGITS
     have
    0.47
     servicing
    0.47
     reconnaître
    0.46
     tööt
    0.45
     They
    0.43
     work
    0.43
     shaker
    0.42
     sounds
    0.42
     take
    0.42
     outperform
    0.42
    Activations Density 0.001%

    No Known Activations