© 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. 172245
    Prev
    Next
    INDEX
    Explanations

    web hosting

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

    inquiring about questions

    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
    žne
    0.49
     réalis
    0.47
    ΄
    0.47
     Croatian
    0.46
    醣
    0.46
    ือด
    0.45
     posiad
    0.44
     Northern
    0.44
    슴
    0.44
    粵
    0.44
    POSITIVE LOGITS
     Imágenes
    0.55
     imágenes
    0.50
     áng
    0.50
     árbol
    0.50
     Ángeles
    0.49
     embers
    0.49
     vacaciones
    0.48
     organizaciones
    0.47
     comrades
    0.47
     naciones
    0.47
    Activations Density 0.000%

    No Known Activations