© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172023
    Prev
    Next
    INDEX
    Explanations

    equal or same

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

    crucial; famous; represent

    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
    Negative Logits
    MP
    0.52
    ర్భ
    0.47
    XK
    0.47
    CG
    0.47
    ructure
    0.47
    Sequence
    0.47
    繕
    0.47
    Aspect
    0.46
    XS
    0.46
    ەش
    0.45
    POSITIVE LOGITS
     igual
    0.54
     doença
    0.50
     Igual
    0.49
    🌯
    0.49
     aiguë
    0.49
     buona
    0.48
     égal
    0.48
     handshake
    0.47
     infraction
    0.47
     Gestion
    0.46
    Activations Density 0.000%

    No Known Activations