© 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. 24761
    Prev
    Next
    INDEX
    Explanations

    explaining or describing

    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
    𝗻
    0.52
     зао
    0.50
     новом
    0.50
    ни
    0.48
    𝗰
    0.47
     নল
    0.46
    柤
    0.44
     neuen
    0.43
    дав
    0.43
    <unused1865>
    0.43
    POSITIVE LOGITS
     ruthless
    0.49
     rousing
    0.49
     apostle
    0.49
     cursory
    0.48
     Shipping
    0.47
     unstoppable
    0.46
     pilgrimage
    0.46
    tier
    0.45
     dreaded
    0.45
     aforesaid
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.