© 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. 97061
    Prev
    Next
    INDEX
    Explanations

    word pairs forming common phrases

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

    show support

    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
     Roger
    0.55
     Tote
    0.51
    singer
    0.51
     wondrous
    0.50
    ruiting
    0.48
     Joe
    0.46
    狍
    0.46
    പറ
    0.46
     Aster
    0.46
     cunning
    0.46
    POSITIVE LOGITS
     typology
    0.50
     BOU
    0.49
     প্রচ
    0.47
     sensitization
    0.46
     WHEN
    0.46
    '
    0.45
     sensit
    0.44
     estimations
    0.44
    ÉN
    0.44
    恋愛
    0.44
    Activations Density 0.001%

    No Known Activations