© 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. 3419
    Prev
    Next
    INDEX
    Explanations

    end of sentence with emphasis

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

    capabilities and formats

    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
     bzw
    0.29
     ४
    0.27
     gruesome
    0.26
     diameters
    0.25
    े
    0.25
    ('
    0.25
     dirinya
    0.24
     त
    0.24
     radii
    0.24
     ७
    0.24
    POSITIVE LOGITS
     يمكنك
    0.27
    你可以
    0.27
     puedes
    0.26
     Although
    0.26
     Obtaining
    0.26
     Gambling
    0.25
     Realtors
    0.25
     Usually
    0.25
     Unlike
    0.25
    إذا
    0.24
    Activations Density 0.721%

    No Known Activations