© 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. 249241
    Prev
    Next
    INDEX
    Explanations

    linking phrases or definitions

    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
    轺
    0.54
    ราะห์
    0.51
     sentencia
    0.48
    ോഗ
    0.46
     emisión
    0.46
     received
    0.46
    FTWARE
    0.46
     korrekt
    0.46
    Received
    0.45
     hoved
    0.45
    POSITIVE LOGITS
    (.*
    0.47
    itals
    0.45
    🐼
    0.44
     టా
    0.43
    irmi
    0.42
    erequisite
    0.42
     стану
    0.42
    uter
    0.41
    .*
    0.41
     જા
    0.41
    Activations Density 0.000%

    No Known Activations