© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6803
    Prev
    Next
    INDEX
    Explanations

    plural suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ast
    1.20
    ρχ
    1.19
    ata
    1.07
    ás
    1.06
    aze
    1.02
     por
    1.02
    ase
    0.99
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.98
     tab
    0.98
    ace
    0.97
    POSITIVE LOGITS
    regarding
    1.95
    providers
    1.91
     comparatively
    1.87
    therly
    1.86
     exceedingly
    1.81
    synthetic
    1.77
    south
    1.76
     conveyance
    1.73
     exceptionally
    1.71
     effortless
    1.70
    Activations Density 0.024%

    No Known Activations