© 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. 116964
    Prev
    Next
    INDEX
    Explanations

    Romeo and Juliet Guide

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

    impacts design, customize your, repeated addition

    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
     CASA
    0.56
     Medic
    0.48
     Libro
    0.47
     Chry
    0.47
    舉
    0.47
     Milch
    0.47
     MATRIX
    0.46
     Sphinx
    0.46
     matriz
    0.45
     CZ
    0.45
    POSITIVE LOGITS
     எனும்
    0.47
    respective
    0.46
    తో
    0.46
    मॉन
    0.46
    >′
    0.45
    aln
    0.45
    aların
    0.44
     оку
    0.44
    ous
    0.44
    лэ
    0.43
    Activations Density 0.000%

    No Known Activations