© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10186
    Prev
    Next
    INDEX
    Explanations

    only a few

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

    difficulty and insufficiency

    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_40_width_16k_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
     неожидан
    0.49
     unexpected
    0.49
     Unexpected
    0.48
    较大
    0.48
    Unexpected
    0.47
     unexpectedly
    0.45
     relativement
    0.45
    较
    0.44
     underrated
    0.44
     mellow
    0.44
    POSITIVE LOGITS
     barely
    1.77
     scarcely
    1.42
     hardly
    1.39
     Hardly
    1.21
     едва
    1.09
     apenas
    0.92
     rarely
    0.82
     paltry
    0.80
     겨
    0.80
     guère
    0.80
    Activations Density 0.499%

    No Known Activations